# Exmergo — AI Agents for Data Analytics > Turn messy data into beautiful, interactive dashboards in minutes. No code required. Exmergo Viz is the Dashboard AI Agent — a SaaS platform where you upload data, ask questions in natural language, and receive interactive dashboards generated autonomously by AI. Start free today at https://viz.exmergo.com. ## How It Works ### Step 1: Upload or connect your data Securely add your datasets and manage them from a centralized Data Hub. Exmergo supports structured files such as CSV and Excel, as well as live Data Connectors, and lets you reuse the same data across multiple dashboards and analyses with full traceability. ### Step 2: Explore your data with AI Interact with your data using natural language. Ask questions, request rankings or comparisons, and let Exmergo's AI analyze your datasets in real time to deliver clear, contextual insights. ### Step 3: Visualize and analyze instantly Turn your data into interactive visualizations in minutes. Exmergo generates charts and analytical views that help you uncover trends, compare metrics, and share insights effortlessly. ## Core Features - Interactive dashboards with multiple visualization types - Transparent, step-by-step AI analysis pipeline - Centralized data hub with lineage and traceability - Supports CSV, Excel, and live database connections (Enterprise) - One-click publish and share — no login required for viewers ## Exmergo Enterprise Exmergo Enterprise packages Dex and Viz together, so analytics engineers and business users work off the same governed foundation. Dex keeps the semantic layer correct for the engineers who maintain it, Viz turns that same governed model into self-serve dashboards for everyone else, and RBAC, PII policy, and full audit trails connect the two, end to end. Learn more at https://www.exmergo.com/enterprise. ## Frequently Asked Questions **What is Exmergo Viz?** Exmergo Viz is a Dashboard AI Agent — a SaaS platform that uses AI agents to turn raw data into interactive dashboards in minutes. You ask questions in natural language and the AI handles the querying, analysis, and visualization. No code required. **How is Exmergo Viz different from tools like Tableau, Power BI, or ChatGPT?** Legacy BI tools like Tableau and Power BI are powerful but require weeks of setup and dedicated analysts. ChatGPT is approachable but produces one-off answers, not persistent dashboards. Exmergo Viz is AI-native and purpose-built for dashboards: you get the accuracy of BI with the ease of chat. **Do I need to know SQL or code to use Exmergo Viz?** No. Exmergo Viz is built for non-technical users. You upload data, ask questions in plain English, and the AI agents generate the queries, run the analysis, and build the charts for you. **What data sources does Exmergo support?** Every plan supports CSV and Excel file uploads. Enterprise plans also support live connections to SQL Server, MySQL, PostgreSQL, and HubSpot, with Google Analytics connectors coming soon. **How much does Exmergo Viz cost?** Exmergo Viz has a free tier (no credit card required), Pro at $19/month, Ultra at $99/month, and Enterprise plans with custom pricing and unlimited users. **Is my data used to train Exmergo's AI?** On paid tiers (Pro, Ultra, Enterprise), your data, prompts, and schema are never used to train AI models. On the free tier, prompts and data samples may be used to refine models. --- # Exmergo Viz — The Dashboard AI Agent > From your data to reliable dashboards. Chat-to-chart at the speed of AI. Exmergo Viz is a SaaS platform that uses AI agents to turn raw data into interactive dashboards. Users interact with their data through natural language — upload a file or connect a live data source, ask a question in plain English, and the AI parses the question, validates the data, runs the analysis, and generates the visualization autonomously. No SQL, no calculated fields, no dashboard-building expertise required. ## How it works - **Upload or connect your data.** Every plan supports CSV and Excel file uploads. Enterprise plans add live connections to SQL Server, MySQL, PostgreSQL, and HubSpot, with Google Analytics connectors coming soon. - **Ask in plain English.** Chat with your data to get rankings, comparisons, trends, and breakdowns — the AI generates the underlying query and runs it against your actual data. - **Get a trustworthy answer.** Viz shows its work at each step — how it interpreted the question, what data it used, how it produced the chart — so you can verify a number instead of just trusting it. - **Publish and share.** One-click publishing creates a read-only public link. Only aggregated query results are shared; raw data is never exposed to viewers. ## Pricing Exmergo Viz has a free tier (no credit card required), Pro at $19/month, Ultra at $99/month, and Enterprise plans with custom pricing and unlimited users. ## Enterprise Exmergo Enterprise packages Viz together with [Exmergo Dex](https://www.exmergo.com/dex), the analytics engineering toolkit that maintains the semantic layer underneath. Dex keeps the model correct for the engineers who build it; Viz turns that same governed model into self-serve dashboards for everyone else, with RBAC, PII policy, and full audit trails connecting the two. Read more: [Why Exmergo Viz](https://www.exmergo.com/viz/why-exmergo-viz) for a feature-by-feature breakdown, or [Data Connectors](https://www.exmergo.com/connectors) for the full connector list. --- # Exmergo Dex > Analytics engineering for Claude Code and any agent: data warehouse exploration, dbt transformation and semantic modeling, and schema-drift maintenance on dbt. Exmergo Dex is the agent-native analytics engineering toolkit. Point it at your warehouse (or a local DuckDB file) and your dbt project; it learns the landscape, writes and refactors your dbt transformations and semantic models, and tells you what to fix when anything drifts. The dbt project is the source of truth, every change is a reviewable diff, and it is read-only against your data. Dex is open source under Apache 2.0. ## The cost squeeze: why Dex exists Data and analytics teams are stuck between a rock and a hard place. On one side, the warehouse bills every scan: Snowflake and Databricks are some of the most expensive consumption-billed software on the planet, and an agent left to explore freely explores on your credit card. On the other, the agent bills every token: Anthropic and OpenAI bill by the token, and nothing burns through a context window faster than data analytics. Dex answers both. It forces the agent to clear a cost guard before it runs an exploration query or a transformation, and it gives the agent a set of tooling that makes it hard to get burned when transforming data. Both come from tight control scripts that the SKILL.md files point the agent at, on every `/dex:explore`, `/dex:transform` and `/dex:maintain`. The guardrails are not a tax on quality. On dbt Labs' 75-task ADE-bench, Dex with Claude Sonnet 5 resolves 76% of tasks, for about 2.5x less than the same loop on Claude Fable 5. See `/benchmarks/ade-bench` for the full results and every published run. ## The loop: Explore, Transform, Maintain (ETM) - **Explore** an unfamiliar warehouse. Dex ranks what matters, profiles columns, infers and verifies joins, and answers ad-hoc questions with guarded SQL probes behind a PII-aware query firewall, then persists a draft map to `.dex/`. Fully read-only. PII is automatically flagged and never surfaced. - **Transform** the dbt project. Dex authors dbt models from staging to marts with tests and docs, and the semantic layer on top (entities, dimensions, measures, metrics) as dbt semantic models (MetricFlow YAML), with a free Viz preview. It also authors the semantic layer as native Apache Ossie documents, for a repository that declares its semantics in the vendor-neutral standard instead of, or beside, dbt. Every change is a reviewable diff, validated against a dev target and cost-guarded. - **Maintain** the project as it drifts. Dex diffs the warehouse and dbt against the last snapshot and surfaces schema, volume, grain, and semantic drift ranked by blast radius, then proposes the reconciling edits. ## Install In Claude Code, run each command one at a time: ``` /plugin marketplace add exmergo/exmergo-agent-plugins /plugin install dex@exmergo ``` The skills appear as `/dex:explore`, `/dex:transform`, and `/dex:maintain` and auto-trigger on matching intent. For any other coding agent (Codex, Gemini CLI, Cursor, and others), the same engine is driven through the command contract documented in `AGENTS.md`: ``` npx skills add exmergo/dex ``` ## Technical guardrails - **Your repository is the source of truth.** Dex does not invent parallel semantic models, whether the layer is declared as dbt semantic models or as Apache Ossie documents. Human edits are authoritative by construction. Dex proposes; you merge. - **Connector-aware cost guard.** Nothing runs without a ceiling. Whether capping bytes-scanned in BigQuery or compute-time in Snowflake, Dex pre-flights and estimates cost before any spend. - **Profile, don't exfiltrate.** Understanding is built from SQL aggregates, not raw rows in context. Credentials and raw data never enter the LLM model context. ## Data handling Dex runs on your machine, inside your own coding agent, using your own warehouse credentials. It has no Exmergo account, no Exmergo server, and no telemetry. Nothing about your data, your queries, or your usage reaches Exmergo. The [Exmergo Dex privacy policy](https://www.exmergo.com/privacy/dex) sets out the full boundary: every destination data can reach, exactly what crosses into your agent's context, how the PII firewall decides what to refuse, and what Dex writes to `.dex/` on disk. ## Connectors Built for the production stack, with a cost guard per connector. | Connector | Cost guard | | --- | --- | | BigQuery | Bytes scanned | | Snowflake | Compute time | | Databricks | DBUs | | Redshift | RPU-hour | | ClickHouse | Compute seconds | | PostgreSQL | Load limit | | DuckDB | Zero-credential on-ramp | ### Semantic layers Dex reads and authors two semantic-layer formats. The dbt semantic layer (MetricFlow), local or through dbt Cloud, and [Apache Ossie](https://github.com/apache/ossie) (incubating), the vendor-neutral standard for exchanging semantic metadata across analytics, BI, and AI platforms. Ossie is native, not a conversion. Install the extra with `pip install 'exmergo-dex[ossie]'`, set `semantic.vendor: ossie` in `.dex/config.yml`, and list your `.ossie.yaml`, `.ossie.yml`, or `.ossie.json` documents under `semantic.ossie.files`. Dex reads the datasets, fields, relationships, and metrics they declare into the same catalog `/dex:explore` has always returned; declared primary keys, unique keys, and relationships become evidence it uses when profiling tables and verifying joins. `semantic ossie define|update|plan`, applied with `transform apply`, authors documents as reviewable diffs, validated against a content-pinned copy of the Ossie JSON Schema and written byte-for-byte so comments, quoting, and ordering survive. `/dex:maintain` snapshots the layer and reports drift against it. A repository with no dbt project at all is supported: set `project.format: ossie` and there is no dbt project and no MetricFlow anywhere in the path. ## Open-core and Enterprise **Dex (Open, Free, Apache 2.0)** gives you the full ETM loop (explore, transform, maintain), manual on-demand drift detection, and a one-shot Viz preview of your semantic model. **[Dex Enterprise](https://www.exmergo.com/dex/enterprise)** brings that loop into an organization-wide workflow. Data requests become grounded, reviewable dbt changes; scheduled drift becomes a reviewed change or advisory; and execution stays inside infrastructure the customer controls. **What is free and what is Enterprise?** Dex is free and open source under Apache 2.0, including the full Explore, Transform, Maintain loop with manual drift detection. Dex Enterprise brings that loop into an organization-wide workflow, turning data requests and scheduled drift into governed, human-reviewed dbt changes inside infrastructure the customer controls. --- # Dex Enterprise: The Agentic Workflow for Your Data Workflows > Turn data work and drift into governed, human-reviewed dbt changes, inside the tools and infrastructure your team already controls. Dex Enterprise brings the open-source Dex analytics-engineering loop into the organization. Data requests and meaningful drift move through one governed path to a draft change or a clear advisory, while your dbt project, review rules, and people remain authoritative. It runs in your CI. It opens a draft change. It never merges it. [Talk to Sales](https://www.exmergo.com/contact-sales) about bringing Dex Enterprise into your data workflow. ## Data Work Never Arrives in One Neat Queue Your team is pulled by requests from people and by changes in the systems underneath them. Both demand context, judgment, and a change someone can review. - **Requests from people** arrive on their schedule: a new metric, a model duplicated after a backfill, a definition that has to match finance. Each one waits on whoever holds the context. - **Drift from systems** arrives without warning: a source column dropped, a table that lost its unique key, a metric that no longer matches the business. It is usually found by whoever trusted the number. Both end in something your team can review, along one path: 1. **Grounded.** Reads your dbt project and warehouse before it writes anything. 2. **Authored.** Model SQL, tests, and semantic definitions in your project's layout. 3. **Validated.** Parsed and built against a dev target, never production. 4. **Reviewed.** A draft change with the run attached. Your reviewers decide. ## Two Workflows. One Review Contract. Whether work begins with a person or a changing warehouse, Dex Enterprise grounds the change in the same dbt project and returns control to your team. ### 01. Requested work: turn the backlog into reviewable dbt changes A request arrives with the context the person gave it. Dex Enterprise grounds that request in your project and your warehouse, authors the change, validates it against a dev target, and hands back a draft pull request tied to the work that asked for it. What the reviewer opens is a normal draft pull request on a Dex branch: the changed model SQL, schema file, and semantic definition with their diff counts, and a run-evidence block recording what the change was grounded in, that every reference and grain resolved, that the dev build passed on the dev target, and which work item asked for it. Review is required, with no bypass for the Dex identity. ### 02. Continuous maintenance: turn drift into action before it becomes breakage A scheduled check compares the warehouse against the baseline your team accepted. Findings arrive grouped rather than one alert at a time, and each one resolves into either a proposed change or an advisory that names the decision a person needs to make. A nightly check reports all four axes, including the ones with nothing to say. A dropped source column becomes one reconcile change across the models that reference it. A grain that no longer holds becomes an advisory, because the fix is a definition decision rather than a mechanical edit. Repeat findings are deduplicated and cooled off, not filed again, and the accepted baseline advances only when a person accepts it. ## You Get a Diff, Its Evidence, and a Decision to Make The thing that lands in your repository is reviewable the ordinary way: a small change in your project's own layout, with the run that produced it attached, and nothing merged on your behalf. - **Grounded, or it stops.** Every change is authored against your dbt project and warehouse as they were read during that run. If a reference cannot be resolved in that evidence, the run refuses to author rather than guessing at a column or a join. - **Validated on a dev target.** The change is parsed and built before you see it, against a dedicated dev namespace with no production write. If the build fails, the draft says so. It is never described as verified when it is not. - **A diff, not a description.** Model SQL, schema tests, and semantic definitions, written in the paths your project already uses. You review a normal pull request, with the same rules and the same reviewers as any other change, and a review comment starts another grounded run rather than a conversation with a model. - **Quiet by design.** Findings are fingerprinted, grouped, capped, and cooled off, so a recurring problem does not become a recurring notification. An unrecognised finding becomes an advisory, never an edit. ### What a Run Can Propose Dex Enterprise proposes familiar analytics-engineering changes. Configuration and governance remain under human control. - **Authored**, proposed as a draft change for review: model SQL, tests and documentation, semantic definitions, and changes in your analytics project. - **Advisory only**, named for a person to decide and never built or published unattended: changes requiring design judgment, project configuration, dependencies, and other work that needs an owner. - **Outside the workflow:** repository governance and system configuration stay with your team, including review and merge rules, workflow configuration, access and policy settings, and anything outside your analytics project. ## The Engine That Writes the Change Is Open Source Dex Enterprise decides when analytics-engineering work runs and how the result reaches your team. The analytics engineering itself is open-source Dex: Apache-2.0, readable before you buy anything, and measured in public. The organizational workflow owns triggers, scheduling, actor authority, review context, noise policy, and the audit trail. Open-source Dex owns warehouse access and project understanding, dbt and semantic authoring, plan validation and reviewable diffs, four-axis drift detection, reconcile plans and blast-radius ordering, and the cost guard and PII policy. The output of that workflow is a draft change or an advisory, and the next authority is human review. Measured on somebody else's benchmark: - **76% on ADE-bench**, Dex with Claude Sonnet 5, 57 of 75 tasks. - **57.3% on data-eng-bench at k=1**, the highest published figure for any Claude Sonnet 5 configuration. data-eng-bench hands an agent a ticket against a 2,356-model dbt project and scores whether that task's own verifier runs clean afterwards. It is the same shape of work Dex Enterprise runs unattended, scored by somebody who does not sell it. ## Runs in Your Environment. Answers to Your Controls. Workflow execution happens inside the CI environment your organization already governs, using identities and services you control. Inside that boundary: the work item, the CI workflow, the guarded Dex run, the draft pull request, and human review. - **Your identities.** Access and permissions remain under your control. - **Your warehouse.** Your team governs the environment and safeguards around it. - **Your review rules.** Branch protection stays authoritative, with no Dex bypass. - **Your inference provider.** Your account, your region, your retention policy. - **Your secrets.** Credentials remain managed within your environment. - **Your records.** Run history remains with your organization. ### Your Controls Remain Authoritative Dex Enterprise is designed to produce a reviewable proposal within the controls your team already owns, not to act as an independent operator in your systems. - **No merge authority.** It can propose a change, but your repository rules decide what is merged. - **Customer-governed execution.** The run works within the environment and access your team controls. - **Bounded workflow.** A run follows the agreed workflow rather than operating freely in your systems. Exmergo does not receive customer data-plane content. No Exmergo service sits in the workflow run path. The normal output is a draft change. Dex Enterprise does not approve or merge it. What it does not claim: that every proposed change is correct, that every secret is detected, or that a required human review makes a diff safe to merge. Human review is a control, not proof. ## Frequently Asked Questions **What is Dex Enterprise?** Dex Enterprise is the organization-wide workflow for Exmergo Dex. It turns data requests and scheduled drift into governed, human-reviewed dbt changes while the dbt project and the customer's review rules remain authoritative. **How is Dex Enterprise different from open-source Dex?** Open-source Dex gives an individual analytics engineer the complete Explore, Transform, Maintain loop on demand. Dex Enterprise brings that same analytics-engineering foundation into unattended organizational workflows around requests, scheduling, review, and audit. The engine that reads the warehouse and writes the dbt change is the same open-source engine in both cases. **What does Dex Enterprise change in my repository?** An unattended run may propose model SQL, schema tests and documentation, and semantic definitions in the project paths you configure. Configuration, workflow, and repository-governance files remain for a person to decide. Every proposal arrives as a draft change for your normal review process. **What stops the agent from doing something destructive?** Dex Enterprise works within the controls your organization owns and produces a draft change for review. It does not independently approve or merge a change; your repository rules and reviewers remain authoritative. **How does Dex Enterprise avoid flooding my team with pull requests and alerts?** Drift findings are fingerprinted, grouped, capped, and cooled off, so a scheduled check produces one grouped result rather than an alert per finding, and a recurring problem does not become a recurring notification. A finding the engine does not recognise becomes an advisory rather than an edit. The accepted baseline only advances when a person accepts it, so a scheduled run never quietly redefines what good looks like. **Does Dex Enterprise run in Exmergo's cloud?** No. Dex Enterprise workflow execution runs in the customer's CI environment using identities and services the customer controls. Exmergo does not receive customer data-plane content, and no Exmergo service sits in the workflow run path. **Does the model see our data?** Dex Enterprise is designed to keep execution in your environment and to avoid sending customer data-plane content to Exmergo. Your organization controls the inference provider, account, region, and retention posture used by the workflow. **How are warehouse and model costs controlled?** The open-source engine estimates billable work before it runs it, gates it against a per-command ceiling and a cumulative session ceiling, caps results, and settles actual spend. Workflow policy can lower that ceiling for a given run but can never raise it. Because the run is in your environment, your own warehouse timeouts, resource monitors, statement limits, and billing alerts remain an independent second brake. **Can Dex Enterprise merge changes automatically?** No. The normal output is a draft change for human review. Dex Enterprise does not intentionally approve or merge it; the customer's repository rules and reviewers decide what becomes part of the dbt project. The publishing step contains no merge or approval operation, and your branch protection is expected to require independent review with no bypass for the Dex identity. **What happens when a reviewer asks for a change?** A reviewer can ask for another pass through the same governed workflow. The change is reconsidered against the current project and returns as another reviewable draft, with your team deciding whether and when to proceed. **What does the audit trail contain?** Each run leaves a record of the workflow and the draft it produced. Content is excluded by default, and the record remains with your organization for your own audit and review processes. **What does Dex Enterprise work with?** It runs against a dbt project in version control, on the warehouse that project already targets, using the same connectors as open-source Dex. We work with design partners to fit Dex Enterprise into the systems and workflows their teams already use. **Is Dex Enterprise available today?** Dex Enterprise is being developed with design partners and is not generally available. Data teams can apply to discuss the workflows they want to improve. ## Design Partnership We are working with a small group of data teams to shape Dex Enterprise around the workflows they need to run continuously, without giving up review, governance, or control. What the conversation covers: the requests and maintenance work your team absorbs today, how a change gets reviewed and merged in your repository, and where an unattended run would have to stop and ask a person. What we look for: a dbt project in version control with review required to merge, a warehouse your team already governs and CI you already run, and a person who owns what a definition means. [Apply as a Dex Enterprise design partner](https://www.exmergo.com/contact-sales?type=dex-enterprise), or [start with open-source Dex](https://www.exmergo.com/dex). --- # Exmergo Ace: The Agent Context Engine | Exmergo > Exmergo Ace is the Agent Context Engine. It turns your governed semantic layer into agent-ready context, so every agent (Exmergo Viz, your own custom agents, and the coding agents your team uses) grounds on one audited source, under the same RBAC, PII policy, and audit. Agents are only as good as the context they stand on. Point them at raw SQL and they invent joins, miss metric definitions, and surface data they were never meant to see. Ace sits between your governed semantic layer and every agent that consumes it, serving grounded, permission-aware context so answers stay correct, consistent, and auditable, no matter which agent asks. Many agents, one governed context. ## The Agent Context Engine Ace is the single context interface every agent connects to. It turns the dbt models, metrics, and join paths that Dex maintains into structured, agent-ready context, so agents reason over real definitions instead of guessing at schemas. The same governed layer is open to Exmergo Viz, any custom agent your team builds, and the coding agents you already use. ## Capabilities ### One interface, every agent Ace is the single context interface every agent connects to. Exmergo Viz, your own custom agents, and the coding agents your team already uses all read from the same place. - One connection point for Viz, custom agents, and coding agents - No bespoke integration per agent: connect once, ground everywhere - Add a new agent without re-plumbing your data access ### Grounded context, not raw SQL Ace serves your dbt models, metrics, and join paths as structured, agent-ready context. Agents reason over definitions instead of guessing at schemas. - Metrics and dimensions served with their real definitions - Verified join paths, so agents never invent relationships - Answers that match the numbers your team already trusts ### Governed by default Opening your data to agents should not mean opening it up. Ace enforces your access model on every request, so each agent sees only what it is allowed to. - Role-based access control and workspace-level permissions - PII policy enforcement on every agent query - Full access audit trails, from prompt to answer ### Always in sync Ace grounds on the same governed layer Dex maintains, so agents never work from a stale copy. When the semantic layer changes, every agent sees it. - One source of truth shared by every consumer - Definitions stay current as Dex authors and maintains them - No drifting exports or duplicated modeling per agent ## How Ace Works 1. **Point Ace at your governed layer.** Ace connects to the dbt models and semantic layer Dex maintains as your single source of truth. 2. **Ace serves agent-ready context.** Definitions, metrics, and join paths become grounded, permission-aware context, never raw SQL. 3. **Every agent queries one source.** Viz, your custom agents, and coding agents all ground on the same audited layer, under the same RBAC, PII policy, and audit. ## Governed From the First Query Ace applies your access model to every agent request, so grounding more agents never widens your exposure. - Role-based access control (RBAC) and workspace-level permissions - PII policy enforcement on every agent request - Full access audit trails for every agent and query - Clear lineage, from governed model to agent answer ## Frequently Asked Questions **What is Exmergo Ace?** Ace is Exmergo's Agent Context Engine. It sits between your governed semantic layer and the agents that consume it, turning dbt models, metrics, and join paths into agent-ready context. Every agent, Exmergo Viz and any custom agent you build, grounds on the same audited layer through Ace, under the same RBAC, PII policy, and access audit. **How is Ace different from connecting an agent straight to my warehouse?** A raw warehouse connection gives an agent tables and SQL, so it has to guess at joins, metric definitions, and which columns it may read. Ace serves the governed semantic layer instead: verified join paths, real metric definitions, and permission-aware context. Agents reason over meaning rather than schema, and every request is bound by RBAC and PII policy. **Which agents can use Ace?** Ace is one context interface every agent connects to: Exmergo Viz for self-serve dashboards, any custom agent your team builds, and coding agents such as Claude and Cursor. Connect once and every agent grounds on the same source, with no bespoke integration per agent. **How does Ace keep agents from drifting out of sync?** Ace grounds on the same governed dbt models and semantic layer that Dex authors and maintains, so there is one source of truth rather than a copy per agent. When a definition changes, every agent sees the change, so answers stay consistent across Viz and your own agents. **Is Exmergo Ace available today?** Not yet. Ace is in private preview and is not generally available. It will be part of the Exmergo Enterprise platform, which today includes Exmergo Viz and Exmergo Dex. We are working with a small group of design partners while we build it, and you can apply to join them: https://www.exmergo.com/contact-sales ## Become an Ace design partner Ace is in private preview. We are working with a small group of design partners to ground their agents on one governed context layer, and shaping Ace around what they need. Apply here: https://www.exmergo.com/contact-sales --- # Exmergo Viz — The Dashboard AI Agent > Exmergo Viz turns your raw data into clear, interactive dashboards — powered by AI, designed for your team. See how Exmergo Viz transforms raw data into interactive, AI-powered dashboards your team can trust. ## Core Features ### Interactive Dashboards and Visual Analytics Viz transforms your data into interactive dashboards with multiple visualizations. Users can explore patterns, compare metrics, and understand results through clear charts and contextual explanations. ### Transparent, Step-by-Step Analysis Viz shows how insights are produced — from understanding the question to validating data and generating visualizations. This transparency builds trust and helps users understand each step of the analysis process. ### Upload or Connect Your Data Upload files or connect to your data sources to start building dashboards instantly. Supports CSV, Excel, and (on Enterprise plans) live connections to SQL Server, MySQL, and PostgreSQL. ### Manage Your Data Sources Search, filter, track usage, and delete data sources from a single interface. Every data source tracks which dashboards depend on it. ### Understand Data Usage Across Dashboards See exactly which dashboards depend on each file and navigate to them instantly. Full lineage and traceability built in. ### Publish and Share Your Dashboards One-click publishing creates a read-only public link — no login required for viewers. Raw data is never exposed; only aggregated query results are shared. ## Frequently Asked Questions **What does it mean that Exmergo Viz is an AI agent for dashboards?** Exmergo Viz uses AI agents — not just a chatbot — to carry out an end-to-end data workflow: it parses your question, validates the underlying data, runs the analysis, and generates the visualization autonomously. The agent shows its work at each step so you can trust the result. **How long does it take to build a dashboard in Exmergo?** Minutes. Upload a CSV, ask a question in plain English, and you have an interactive dashboard. No data modeling, no calculated fields, no gateway setup. **Does Exmergo show how it arrived at an insight?** Yes. Exmergo's step-by-step analysis view shows how the AI interpreted your question, what data it used, and how it produced the chart. You should never have to trust a number you can't explain. **Can I share dashboards without exposing the underlying data?** Yes. Published dashboards are read-only snapshots that save only the query results — never the raw data. You can share a link with anyone without granting access to your source files. **How does Exmergo avoid AI hallucinations?** Exmergo Viz is grounded on your actual data. The AI generates structured queries that run against your uploaded data or connected database, and the visualizations reflect real query results — not model-generated text. --- # Pricing — Exmergo > Our pricing for AI-powered data visualization is simple and controllable. Start free with 250 daily AI credits, or upgrade to Pro, Ultra, or Enterprise for more power and flexibility. Exmergo Viz offers four plans. The free tier requires no credit card. Pro and Ultra include a 14-day free trial. Enterprise is custom priced with unlimited users and no per-user pricing. Exmergo Dex is free and open source for individual, on-demand use. [Dex Enterprise](https://www.exmergo.com/dex/enterprise) brings Dex into an organization-wide workflow. ## Plans ### Free — $0/month For individuals exploring AI-powered analytics. - 250 Daily AI Credits - Unlimited Dashboards - Share with Anyone - 1 Table per Dashboard - 30 MB Dashboard Storage - 15 GB Account Storage ### Pro — $19/month (or $192/year — save 16%) For professionals who need more power and flexibility. - 5,000 Daily AI Credits - Unlimited Tables in Dashboard - Join Tables within Dashboard - 250 MB Dashboard Storage - 2 TB Account Storage - Collaborative Workspaces - Remove Watermark from Charts - 14-day free trial included ### Ultra — $99/month (or $996/year — save 16%) For power users and growing teams with heavy workloads. - 20,000 Daily AI Credits - Unlimited Tables in Dashboard - Join Tables within Dashboard - 500 MB Dashboard Storage - 50 TB Account Storage - Collaborative Workspaces - Remove Watermark from Charts - 14-day free trial included ### Enterprise — Custom pricing For organizations that need full control and scale. Custom pricing, unlimited users. - Everything in Ultra - Unlimited AI Credits - Unlimited Users - Live Data Connectors - Exmergo Ace for Every Agent - Enterprise IAM & RBAC - Enterprise Support ## Exmergo Ace (private preview) Exmergo Ace is the Agent Context Engine. It serves your governed semantic layer to Exmergo Viz, the custom agents you build, and the coding agents your team already uses, as grounded, permission-aware context rather than raw data. Ace is in private preview with design partners and is not generally available. It will be included in every Exmergo Enterprise tier (Standard Cloud, Private Managed Cloud, and On-Premise), with no per-agent fee and no bespoke integration to maintain. - One connection point for Viz, custom agents, and coding agents - Metrics, dimensions, and verified join paths served with their real definitions - RBAC, PII policy enforcement, and full audit trails on every agent request Ace is enterprise-only today, so it is not included in the Free, Pro, or Ultra plans. ## Dex Enterprise Dex Enterprise turns data requests and scheduled drift into governed, human-reviewed dbt changes inside the tools and infrastructure your team already controls. [Explore Dex Enterprise](https://www.exmergo.com/dex/enterprise) or talk to our team about your workflow. ## Frequently Asked Questions **Can I switch plans at any time?** Yes. You can upgrade, downgrade, or cancel your plan at any time from your account settings. Changes take effect immediately. All your dashboards and data remain fully accessible. **What happens when I run out of daily AI credits?** Daily AI credits reset every 24 hours at 00:00 UTC. If you hit your limit, you can wait for the reset or upgrade to a plan with more credits. Your dashboards and data remain fully accessible. **How does annual billing work?** Annual billing gives you a 16% discount compared to monthly. You pay once per year upfront, and can switch to annual billing at any time from your account. **Is there a free trial for paid plans?** Yes. Pro and Ultra plans include a 14-day free trial. You can cancel at any time. **What payment methods do you accept?** We accept all major credit cards (Visa, Mastercard, American Express) through Stripe. **What does Enterprise include beyond Ultra?** Enterprise plans include unlimited AI credits, unlimited users, custom data connectors, dedicated support, and flexible deployment options. Contact sales for a tailored quote. **Is Exmergo Ace included in Enterprise pricing?** Yes. Ace, the Agent Context Engine, is included on every Exmergo Enterprise tier: Standard Cloud, Private Managed Cloud, and On-Premise. There is no separate license and no per-agent fee. Ace is enterprise-only today, so it is not part of the Free, Pro, or Ultra plans. **Do I pay per agent connected to Ace?** No. Enterprise is an account-wide license, and Ace is part of it. You can ground Exmergo Viz, the custom agents your team builds, and coding agents such as Claude and Cursor on the same governed context layer without adding cost per agent. **Is pricing per user or per account?** Free, Pro, and Ultra are individual licenses for 1 user each. Enterprise is an account-wide license with unlimited users included. **What is Dex Enterprise?** Dex Enterprise turns data requests and scheduled drift into governed, human-reviewed dbt changes inside infrastructure the customer controls. Talk to our team about bringing it into your data workflow. **Is there a free plan?** Yes. The free tier includes 250 daily AI credits, unlimited dashboards, 15 GB of account storage, and public sharing. No credit card required. --- # Enterprise Solutions | Exmergo > Exmergo Enterprise packages Dex and Viz together, with a governed, audited handoff between analytics engineers and business users. Enterprise-grade security, governance, and support. Every organization has two audiences for its data: the engineers who model it and the business users who need answers from it. Exmergo Enterprise connects them with a governed author-to-serve loop. Dex maintains one semantic layer, Ace turns it into agent-ready context, and Viz plus any custom agent you build ground on the same audited source. Security and control are built in from the start. Enterprise plans are custom priced with unlimited users, with no per-user pricing. ## Why Enterprise Built for the handoff, not just the dashboard. Exmergo Enterprise is the platform that connects the engineers who model your data with the business users who need answers from it. Dex maintains one governed semantic layer, Ace, the Agent Context Engine, makes it ingestible by agents, and Viz plus any custom agent you build ground on the same source. ## Enterprise Capabilities ### Dex for Analytics Engineers Your analytics engineers keep using Dex, the agent-native toolkit that authors and maintains your dbt models and semantic layer. Enterprise turns it from a personal habit into a team-wide practice. - Continuous, scheduled drift detection with automated PRs - Governed dbt models and semantic layer as the single source of truth - Every change is a reviewable diff, never a silent overwrite [Explore Dex Enterprise](https://www.exmergo.com/dex/enterprise), the organization-wide workflow for governed, human-reviewed data work. ### Ace, the Agent Context Engine Ace turns your governed semantic layer into agent-ready context. It is the engine that makes your models, metrics, and join paths ingestible by agents, so every agent grounds on the same audited source instead of raw SQL. - One context interface every agent connects to, from Viz to your own - Definitions, metrics, and join paths served as grounded context, not raw SQL - Governed access: agents see only what RBAC and PII policy allow ### Viz and Your Own Agents Business users get Viz: a chat-driven agent that turns the governed semantic layer into interactive dashboards in minutes, without writing SQL or waiting on a backlog. Through Ace, the same governed layer is open to any custom agent your team builds. - Self-serve dashboards grounded in the same models your engineers maintain - One governed layer, many agents: Viz and every custom agent read from it - Enterprise data connectors for growing volumes and multiple systems ### Security & Governance Standardize decision-making and protect sensitive data while preserving flexibility across teams. - Role-based access control (RBAC) and workspace-level permissions - PII policy enforcement and full access audit trails - Clear data-to-dashboard lineage, from warehouse to chart ### Priority Support - Priority support channels - Enterprise-grade SLAs - Dedicated account manager ## Single-Player vs. Enterprise Single-player is free. The organization-wide loop is Enterprise. **Dex** (Open · Free · Apache 2.0) - Full explore, transform, maintain loop for one engineer - Manual, on-demand drift detection - One-shot Viz preview of your semantic model **Exmergo Enterprise Platform** (Everything in Dex, plus:) - Continuous, scheduled drift detection with automated PRs - A live author-to-serve loop: Dex authors, Ace serves Viz and your agents - Cross-team governance, PII policy, and access audit ## A Platform You Can Trust - Role-based access control (RBAC) - Auditability and traceability - Secure data handling and isolation - Designed for cloud and hybrid environments ## Deployment Options - **Standard Cloud**: Shared infrastructure with logical data isolation. - **Private Managed Cloud**: Dedicated infrastructure with physical isolation and geo-location control. - **On-Premise**: Deployed on your own infrastructure with forward-deployed engineers. ## Proof-of-Value Trials - Standard Cloud: reduced-price 3-month trial (200,000 AI credits included) - Private Managed Cloud: reduced-price 3-month trial (200,000 AI credits included) ## Frequently Asked Questions **What is Dex Enterprise?** Dex Enterprise brings the open-source Dex analytics-engineering loop into an organization-wide workflow. It turns data requests and scheduled drift into governed, human-reviewed dbt changes inside infrastructure the customer controls. **Does Exmergo Enterprise include Dex as well as Viz?** Yes. Exmergo Enterprise packages Dex for the analytics engineers who author and maintain your dbt models and semantic layer, and Viz for the business users who need self-serve dashboards from it. The same governed semantic layer is also open to any custom agent your team builds, so every consumer works from one audited source instead of drifting apart. **What is Exmergo Ace?** Ace is Exmergo's Agent Context Engine. It sits between your governed semantic layer and the agents that consume it, turning dbt models, metrics, and join paths into agent-ready context. Every agent, Viz and any custom agent you build, grounds on the same audited layer through Ace, under the same RBAC, PII policy, and access audit. **Can we build our own agents on Exmergo Enterprise?** Yes. Dex maintains one governed semantic layer as the single source of truth, and Ace, the Agent Context Engine, makes it ingestible by many agents: Viz for self-serve dashboards, plus any custom agent your team builds on top of it. Every agent reads from the same audited models through Ace, under the same RBAC, PII policy, and access audit, so nothing drifts from a stale copy. **What is the governed handoff between Dex and Viz?** Dex is free and open source for a single engineer working locally. Exmergo Enterprise upgrades that into a live, governed author-to-serve loop: continuous scheduled drift detection with automated PRs on the Dex side, and Ace, the Agent Context Engine, serving that layer as agent-ready context to every consumer on the other side, Viz and any custom agent you build, always grounded in the same audited semantic layer, with cross-team governance, PII policy, and access audit connecting them. **How is Exmergo Viz priced at the enterprise level?** Enterprise pricing is tailored to your organization, based on your deployment tier (Standard Cloud, Private Managed Cloud, or On-Premise) and capacity. Every tier includes unlimited users, with no per-user pricing. Contact sales for a quote. **Does Exmergo support SSO, RBAC, and enterprise security?** Yes. Enterprise plans include IAM and RBAC with workspace-level permissions, collaborative workspaces, company-level AI credit budgets, full audit trails and data lineage, and enterprise-grade security. **Is customer data used to train the AI on enterprise plans?** No. On Pro, Ultra, and all Enterprise plans, your data, prompts, and schema are never used to train AI models. **Can Exmergo be deployed on our own infrastructure?** Yes. The On-Premise tier deploys Exmergo Enterprise on your own infrastructure with full data isolation, custom release management, and forward-deployed engineers. **Is there a proof-of-value trial for enterprises?** Yes. Exmergo offers reduced-price 3-month trials for Standard Cloud and Private Managed Cloud, each including 200,000 AI credits. Contact sales for details. ## Contact Sales Talk to our team about deploying Exmergo Enterprise, Dex and Viz together, at scale: https://www.exmergo.com/contact-sales --- # Data Connectors — Exmergo > Connect Exmergo Viz to your enterprise data sources. Query live data, build dashboards, and monitor metrics in real time. Exmergo Viz supports file uploads on all plans and live database connectors on Enterprise plans. ## Available Connectors ### Databases (Available now) **SQL Server** Connect to Microsoft SQL Server databases for enterprise data warehousing, reporting, and analytics. **MySQL** Query MySQL databases directly. Ideal for web applications, SaaS platforms, and operational data. **PostgreSQL** Connect to PostgreSQL for advanced analytics, geospatial data, and complex queries on structured data. ### CRM (Available now) **HubSpot** Pull marketing, sales, and customer data from HubSpot to visualize your funnel and campaign performance. ### Marketing (Coming Soon) **Google Analytics** Connect to Google Analytics to visualize your website traffic, user behavior, and marketing campaigns. ## File Uploads (All Plans) All plans — including the free tier — support CSV and Excel file uploads. Files are converted to Apache Parquet format and stored privately on Google Cloud Platform. ## Connector Categories - **Databases**: SQL Server, MySQL, PostgreSQL - **CRM**: HubSpot - **Marketing**: Google Analytics (coming soon) ## Frequently Asked Questions **Which databases does Exmergo Viz connect to?** Exmergo Viz connects to SQL Server, MySQL, PostgreSQL, and HubSpot on Enterprise plans. Google Analytics connectors are coming soon. **Can I upload CSV and Excel files?** Yes. All plans — including the free tier — support CSV and Excel file uploads. Files are converted to Apache Parquet format and stored privately on Google Cloud Platform. **Are live database connectors available on all plans?** Live database connectors (SQL Server, MySQL, PostgreSQL) are available on Enterprise plans. Pro and Ultra plans focus on file-based data sources. **Can I combine data from multiple sources in one dashboard?** Yes. Pro, Ultra, and Enterprise plans support joining multiple tables within a single dashboard. The free tier supports one table per dashboard. **Is my data secure when connecting to a database?** Yes. Database connections are encrypted in transit. On Enterprise plans you can configure VPN/VPC access, physical data isolation, and custom geo-location for data residency. --- # Exmergo Benchmarks > How Exmergo performs on public analytics-engineering benchmarks. Every run is published under its own dated page, including the baseline it was compared against. Claims about agent quality are cheap; measured results on a public suite are not. Exmergo runs its products against third-party benchmarks and publishes every run, so the numbers can be checked rather than taken on trust. Each run gets a permanent dated page instead of overwriting the previous one, so older results stay citable and improvements can be traced over time. ## Best result **Dex + Claude Sonnet 5 resolves 57 of 75 tasks (76.0%) on dbt Labs' ADE-bench**, leading three model runs and beating dbt's own published agent skills at 58%. | Run | Resolved | Accuracy | Cost | | --- | --- | --- | --- | | Dex + Claude Sonnet 5 | 57 / 75 | **76.0%** | $35.95 | | Dex + Claude Fable 5 | 56 / 75 | 74.7% | $91.98 | | Dex + Claude Opus 4.8 | 54 / 75 | 72.0% | $43.38 | | Claude Sonnet 5 (no `dex`) | 53 / 75 | 70.7% | $30.76 | With Dex, accuracy holds in a 72–76% band across all three models while cost ranges from $36 to $92, so the practical call is to run an inexpensive model. Full write-up: [ADE-bench, 21 July 2026](https://www.exmergo.com/benchmarks/ade-bench/2026-07-21) ([md](https://www.exmergo.com/benchmarks/ade-bench/2026-07-21.md)) ## Newest result **Dex + Claude Sonnet 5 resolves 59 of 103 tasks (57.3%) on Snowflake's data-eng-bench**, the highest published figure for any Claude Sonnet 5 configuration and statistically indistinguishable from the two Snowflake published at 56.6%. Measured at k=1, one attempt per task, with a 95% confidence interval of 47.6% to 66.4%. Dex was invoked on 98% of trials, and 2,699 of the 2,850 individual verifier assertions passed. There is no baseline arm in that run, so no improvement is attributed to Dex. Full write-up: [data-eng-bench, 11 August 2026](https://www.exmergo.com/benchmarks/data-eng-bench/2026-08-11) ([md](https://www.exmergo.com/benchmarks/data-eng-bench/2026-08-11.md)) ## Benchmarks we run against Public suites published by third parties, not internal test sets. - **[ADE-bench](https://www.exmergo.com/benchmarks/ade-bench)** ([md](https://www.exmergo.com/benchmarks/ade-bench.md)). dbt Labs' 75-task Analytics Engineering Benchmark. Hands an agent a real dbt project on DuckDB and scores whether the project's tests pass afterwards. - **[data-eng-bench](https://www.exmergo.com/benchmarks/data-eng-bench)** ([md](https://www.exmergo.com/benchmarks/data-eng-bench.md)). Snowflake's 103-task Data Engineering Agent Benchmark. Drops an agent into a 2,356-model dbt project with a ticket and scores whether the task's own pytest verifier runs clean. ## All runs - [data-eng-bench, 11 August 2026](https://www.exmergo.com/benchmarks/data-eng-bench/2026-08-11): 57.3% (59/103) at k=1, best run Claude Sonnet 5 with dex. - [ADE-bench, 21 July 2026](https://www.exmergo.com/benchmarks/ade-bench/2026-07-21): 76.0% (57/75), best run Claude Sonnet 5 with dex. ## How we benchmark **Why publish benchmark results at all?** Because a measured result on a public suite can be checked, and a marketing claim cannot. Every run is published with the baseline it was compared against. **Why is every run under its own dated URL?** A benchmark result is only meaningful alongside the date it was measured, the models it used, and the harness configuration. Dated pages keep older results citable. **Are these results reproducible?** Yes. Each run page lists the agent, the models, the number of attempts per task, and the exact plugin configuration used, along with any prompt the run's image added, reproduced verbatim. The suites are public, and the raw per-trial output for every run is committed alongside the harness configuration: under `experiments/` for ADE-bench, and under `benchmarks/data-eng-bench` for data-eng-bench. **What does k=1 mean, and why does it matter?** One attempt per task, with no re-runs and no best-of selection. Snowflake's published data-eng-bench figures are k=3, so theirs is the same measurement on three times the sample and Exmergo's is the noisier estimate. A k=1 run also cannot produce a Pass^3 figure, so none is published. --- # Partner with Exmergo > Join the Exmergo partner ecosystem and collaborate with us to deliver data-driven decision intelligence to organizations. Exmergo operates three partner tiers: Referral, Agency, and Value-Added Reseller. ## Partnership Types ### Referral Partnership Designed for individuals and organizations who want to recommend Viz to their network. Referral partners introduce qualified leads, while Exmergo manages product delivery, onboarding, and support. - Commission-based rewards for successful referrals - Sales and marketing enablement materials - No technical integration or delivery responsibility ### Agency Partnership For agencies, consulting firms, and system integrators that support clients in analytics, performance management, or digital transformation. Offer Viz as part of your service portfolio. - Enable Viz within client projects and engagements - Access to product knowledge and partner support - Opportunities for co-selling and collaboration ### Value-Added Reseller (VAR) For companies that want to bundle Exmergo Viz with their own solutions or services to create a differentiated, high-value offering for their customers. - Package Viz as part of your solution offering - Dedicated technical and commercial support - Joint go-to-market and customer engagement opportunities ## Who Should Partner with Us? Exmergo partners best with organizations and professionals who work closely with data, analytics, and decision-making, and who want to deliver measurable value to their customers. **What we expect from partners:** - A clear understanding of customer needs and how Exmergo supports data-driven decisions - A collaborative mindset focused on long-term value - A commitment to representing Exmergo accurately and responsibly ## Frequently Asked Questions **What types of partnerships does Exmergo offer?** Exmergo operates three partner tiers: Referral (for individuals or organizations recommending Viz to their network), Agency (for consulting firms and system integrators embedding Viz in client engagements), and Value-Added Reseller (for companies bundling Viz into their own solutions). **How does the referral program work?** Referral partners receive commission-based rewards for successful referrals. Exmergo provides sales and marketing enablement materials. There's no technical integration or delivery responsibility. **Can agencies resell or deliver Exmergo Viz to clients?** Yes. Agency partners can enable Viz within client projects and engagements, with access to product knowledge, partner support, and co-selling opportunities. **How do I become an Exmergo partner?** Visit the partnerships page and get in touch through the contact form. The Exmergo partnerships team will walk you through the application and enablement process. ## Become a Partner Contact us at https://www.exmergo.com/contact-sales?type=partnership --- # Blog — Exmergo > Insights on AI Agents applied to Data Analytics, product updates, and industry trends from the Exmergo team. The Exmergo blog covers AI agents for data analytics, product updates, use-case deep dives, and industry trends in the data visualization space. ## Topics We Cover - AI agents applied to data analytics - How teams use Exmergo Viz for dashboards and reporting - Comparisons between AI-native and legacy BI tools - Product updates and new feature announcements - Industry trends in self-service analytics ## About Exmergo Exmergo, Inc. is a Delaware-incorporated company. Its flagship product is Exmergo Viz — a Dashboard AI Agent that turns raw data into interactive dashboards using natural language queries. No code required. Read the latest posts at https://www.exmergo.com/blog --- # Contact Sales — Exmergo > Get in touch with the Exmergo sales team to discuss your data needs, request a demo, or learn more about our enterprise solutions. Talk to the Exmergo team about enterprise plans, custom deployments, partnerships, or getting a live demo of Exmergo Viz. ## What to Expect - A response within one business day - A personalized demo of Exmergo Viz tailored to your data and use case - A discussion of deployment options (Standard Cloud, Private Managed Cloud, On-Premise) - Pricing guidance for your team size and usage requirements ## Enterprise Inquiries Enterprise plans include unlimited users, live data connectors, IAM & RBAC, and enterprise support. Pricing is tailored to your organization, with no per-user charges. Deployment options: - **Standard Cloud** - **Private Managed Cloud** (physical data isolation, geo-location control) - **On-Premise** (deployed on your own infrastructure) ## Partnership Inquiries If you're interested in becoming a Referral, Agency, or Value-Added Reseller partner, use the contact form and select "Partnership" as the inquiry type. ## Contact Email: support@exmergo.com Sales form: https://www.exmergo.com/contact-sales --- # Exmergo Viz vs Tableau — Which Is Right for You? > An honest comparison of Exmergo Viz and Tableau. See where each tool shines — from AI-native dashboards to enterprise visual analytics — and decide which fits your team. Tableau is the industry standard for enterprise visual analytics. Exmergo Viz is the AI-native alternative built for speed. Both are powerful — for different reasons. ## At a Glance | Dimension | Exmergo Viz | Tableau | |---|---|---| | Time to first dashboard | Minutes | Days to weeks | | Learning curve | None — ask questions in plain English | Steep — "Tableau expert" is a job title | | How you build | Conversational AI + drag-and-drop | Drag-and-drop visual builder | | Pricing model | Free tier, $19/mo Pro, $99/mo Ultra. Enterprise: no per-user fees. | Creator $75/user/mo, Explorer $42/user/mo, Viewer $15/user/mo | | Data sources | CSV, Excel, SQL Server, MySQL, PostgreSQL (growing) | 100+ native connectors | | AI capabilities | Core product — AI generates queries, charts, and insights from natural language | Tableau AI and Pulse added as supplementary features | | Ideal team size | 1 to 1,000 — from solo operators to enterprise teams | Best for organizations with dedicated analytics staff | | Deployment | Cloud-native SaaS. Private cloud and on-premise for enterprise. | Tableau Cloud, Tableau Server (on-premise), or embedded | ## What Makes Exmergo Viz Different ### AI-Native, Not AI-Added Tableau added AI features on top of a visual builder designed in 2003. Exmergo was built from the ground up around AI agents. You ask questions in plain English. The AI handles the query, the analysis, and the visualization. ### Minutes, Not Weeks A typical Tableau deployment takes weeks of setup, data modeling, and training. Exmergo Viz: upload a file, ask a question, get a dashboard. No Tableau Desktop install, no Prep Builder, no calculated fields. ### Everyone Can Use It Tableau requires training. Skilled Tableau developers command premium salaries. Exmergo Viz requires no training — if you can ask a question, you can build a dashboard. ### No Per-User Tax Tableau's per-user pricing means costs scale linearly with headcount. A 50-person team on Explorer costs $25,200/year. Exmergo's enterprise plans include unlimited users — your cost doesn't grow with your team. ## When Tableau Is the Better Fit - You need 100+ native data connectors — Salesforce, SAP, Snowflake, Databricks, and more. Tableau's connector ecosystem is unmatched. - You have a mature analytics team with Tableau expertise. If your team already builds complex calculated fields, LOD expressions, and parameter-driven dashboards, Tableau's power is hard to replace. - You need deeply embedded analytics inside other applications. Tableau's embedding SDK and API ecosystem are battle-tested at scale. - You require offline desktop analysis. Tableau Desktop works without an internet connection. Exmergo Viz is cloud-native. ## When Exmergo Viz Is the Better Fit - You don't have dedicated Tableau developers — and you don't want to hire them. Exmergo Viz gives every team member the power to build dashboards with AI. - Your dashboard backlog is growing faster than your team can deliver. Exmergo acts as an AI-powered first line of support — business users get answers instantly. - You need dashboards today, not after a multi-week implementation. Upload your data and start asking questions in minutes. - You want predictable costs without per-user pricing surprises. Exmergo's enterprise plans include unlimited users. - You're a startup or growing team that needs Tableau-level output without Tableau-level complexity or cost. ## The Bottom Line Tableau is a powerful, mature platform built for dedicated analytics teams. Exmergo Viz is an AI-native platform built to make everyone a data analyst. If your challenge is complexity and depth, Tableau might be the right fit. If your challenge is speed, accessibility, and getting dashboards into more hands — that's exactly what Exmergo Viz was built for. ## Frequently Asked Questions **Is Exmergo Viz a Tableau replacement?** It can be — especially for teams who want dashboards in minutes without dedicated Tableau developers. For organizations with deep Tableau expertise or niche connector requirements, Tableau remains a strong choice. Exmergo Viz targets the speed and accessibility gap. **Do I need training to use Exmergo Viz the way I would for Tableau?** No. Exmergo is built for natural-language use. If you can ask a question, you can build a dashboard. Tableau requires training on its visual builder, calculated fields, and LOD expressions. **How does Exmergo Viz pricing compare to Tableau?** Exmergo: free tier, $19/month Pro, $99/month Ultra, custom-priced enterprise with unlimited users. Tableau: Creator $75/user/mo, Explorer $42/user/mo, Viewer $15/user/mo, per-user pricing that scales with headcount. **Does Exmergo have the same number of data connectors as Tableau?** Not yet. Tableau's 100+ connector library is unmatched. Exmergo supports CSV, Excel, SQL Server, MySQL, PostgreSQL, and HubSpot today, with Google Analytics coming soon. --- # Exmergo Viz vs Power BI — Which Is Right for You? > An honest comparison of Exmergo Viz and Microsoft Power BI. See where each tool shines — from AI-native dashboards to Microsoft ecosystem integration — and decide which fits your team. Power BI is Microsoft's business intelligence platform — deeply integrated with the Office 365 and Azure ecosystem. Exmergo Viz is the AI-native alternative that works with any data, anywhere. ## At a Glance | Dimension | Exmergo Viz | Power BI | |---|---|---| | Time to first dashboard | Minutes | Hours to days | | Learning curve | None — ask questions in plain English | Moderate to steep — DAX formulas required for advanced analysis | | How you build | Conversational AI + drag-and-drop | Drag-and-drop with DAX/M formula languages | | Pricing model | Free tier, $19/mo Pro, $99/mo Ultra. Enterprise: no per-user fees. | Power BI Pro $10/user/mo, Premium $20/user/mo, or capacity-based from $4,995/mo | | Data sources | CSV, Excel, SQL Server, MySQL, PostgreSQL (growing) | 100+ connectors, deepest with Microsoft stack | | AI capabilities | Core product — AI generates queries, charts, and insights | Copilot integration, Q&A natural language, AI visuals | | Ecosystem dependency | Standalone — works with any data source, no platform lock-in | Best experience within the Microsoft ecosystem | | Deployment | Cloud-native SaaS. Private cloud and on-premise for enterprise. | Power BI Service (cloud), Power BI Report Server (on-premise), embedded | ## What Makes Exmergo Viz Different ### No Formulas Required Power BI's real power comes from DAX — a formula language with a steep learning curve. Exmergo Viz replaces formulas with natural language. Ask "show me revenue by quarter" and the AI writes the query, runs it, and builds the chart. ### Works With Your Data, Not Just Microsoft's Power BI is at its best when your data lives in Azure, SQL Server, or Excel. Exmergo Viz is platform-agnostic — upload a CSV, connect a database, and start building. No Azure subscription required. ### Instant Time to Value A proper Power BI deployment requires data modeling in Power BI Desktop, publishing to the service, setting up a gateway, and configuring refresh schedules. Exmergo Viz: upload your file and start asking questions. ### Simpler Sharing Sharing Power BI reports requires recipients to have Power BI licenses (Pro or Premium). Exmergo Viz lets you publish dashboards with one click — no license needed for viewers. ## When Power BI Is the Better Fit - Your organization is deeply invested in the Microsoft ecosystem — Azure, Office 365, Teams, SharePoint, Dynamics 365. Power BI's integrations with these tools are seamless. - You need complex data modeling with relationships, calculated columns, and measures. Power BI's data model is enterprise-grade for this. - You need paginated reports (pixel-perfect, printable reports) for regulatory and financial reporting. - You already have Power BI licenses bundled with your Microsoft E5 or F3 agreements. ## When Exmergo Viz Is the Better Fit - You don't want to learn DAX. Exmergo's AI handles the analysis — you just ask questions in the language you already speak. - Your data doesn't live in Microsoft's ecosystem. Exmergo works without Azure or gateway setup. - You want to share dashboards without requiring everyone to have a Power BI license. Exmergo's one-click publishing creates shareable links — no viewer licenses needed. - You need dashboards now, not after setting up a data model, gateway, and refresh schedule. - You're a startup or small team that needs business intelligence without a Microsoft enterprise agreement. ## The Bottom Line Power BI is a strong choice for organizations already committed to the Microsoft stack. Exmergo Viz is for teams who want AI-powered dashboards without platform lock-in, formula languages, or complex setup. If your data lives in Azure and your team knows DAX, Power BI is well-suited. If you want anyone on your team to go from data to dashboard in minutes — that's what Exmergo Viz was built for. ## Frequently Asked Questions **Is Exmergo Viz a Power BI alternative?** Yes, particularly for teams who don't want to learn DAX or commit to the Microsoft ecosystem. Power BI remains a strong choice for organizations already standardized on Azure, Office 365, and SQL Server. **Do I need to learn DAX or M formulas in Exmergo?** No. Exmergo replaces formula languages with natural language. Ask "show me revenue by quarter" and the AI agent writes the query and builds the chart. No DAX, no M, no calculated columns. **How does Exmergo pricing compare to Power BI?** Exmergo: free tier, $19/month Pro, $99/month Ultra, custom-priced enterprise. Power BI: $10/user/month Pro, $20/user/month Premium-per-user, or capacity-based starting at $4,995/month. **Can I share Exmergo dashboards without requiring a license for viewers?** Yes. One-click publishing creates a shareable link anyone can view — no Exmergo account required. Power BI typically requires recipients to have Pro, Premium, or capacity-based access. --- # Exmergo Viz vs ChatGPT — Which Is Right for You? > An honest comparison of Exmergo Viz and ChatGPT. See where a purpose-built dashboard AI agent beats a general-purpose chat assistant — and where each fits. ChatGPT is a great general-purpose assistant. Exmergo Viz is a purpose-built AI agent for data visualization. Both use AI — very differently. ## At a Glance | Dimension | Exmergo Viz | ChatGPT | |---|---|---| | Primary purpose | Building and sharing persistent, interactive dashboards | General-purpose chat assistant for writing, coding, and analysis | | Output format | Interactive dashboards with stable shareable URLs | Chat messages and one-off charts inside a conversation | | Data grounding | Structured queries run against your actual data — no hallucination on numbers | Can hallucinate on numerical or tabular reasoning without careful prompting | | Persistence | Dashboards persist, refresh, and reflect new data over time | Chat threads persist; analyses and charts don't update with new data | | Data sources | CSV, Excel, SQL Server, MySQL, PostgreSQL | File uploads per conversation; ChatGPT Connectors for selected apps | | Sharing | One-click publish — shareable with anyone, no account required for viewers | Shared conversations and canvases — chat transcripts, not dashboards | | Pricing | Free tier, $19/mo Pro, $99/mo Ultra. Enterprise: custom pricing, no per-user tax. | Free tier, Plus $20/user/mo, Team $25/user/mo, Enterprise per-seat | | Data & training policy | On paid tiers, your data, prompts, and schema are never used to train AI models | Policies vary by plan | | Built for | Recurring dashboards, non-technical users, governed enterprise data | Writing, coding, brainstorming, ad-hoc Q&A | ## What Makes Exmergo Viz Different ### Purpose-Built for Dashboards Exmergo's agents are designed for one job: turning data into interactive dashboards. The output is a persistent, shareable dashboard at a stable URL — not a chat transcript. ### Grounded on Your Real Data Exmergo generates structured queries that run against your actual data. Charts reflect real query results, not model-generated numbers. The agent shows its work so you can verify every step. ### One-Click Publish & Share Publish a dashboard with one click and share a link with anyone — no login required for viewers. Published dashboards never expose raw data, only aggregated query results. ### Enterprise Isolation, No Training on Your Data On paid tiers, Exmergo never uses your data to train AI models. Enterprise plans offer physical data isolation, custom geo-location, and on-premise deployment. Data is not sent raw to third-party AI providers. ## When ChatGPT Is the Better Fit - You need a general-purpose AI assistant for writing, coding, brainstorming, or broad Q&A — not specifically dashboards. - You're doing one-off data analysis on small files and don't need a persistent, shareable dashboard at the end. - Your team already has ChatGPT bundled in a plan, and incremental cost matters more than specialization. - You want a chat-first interface for exploring an idea, not a structured dashboarding workflow with governance. ## When Exmergo Viz Is the Better Fit - You need recurring, interactive dashboards that persist, update, and live at a stable URL — not transient chat outputs. - Non-technical users on your team need to build dashboards without learning SQL, Python, or prompt engineering. - You care about avoiding hallucinations on numerical answers — Exmergo grounds every chart in a real query against your data. - You need governed enterprise data: no training on customer data, physical isolation options, and clear data-to-dashboard lineage. - You want to share dashboards with leadership, clients, or the public — with one click, no viewer accounts required. ## The Bottom Line ChatGPT is a powerful general-purpose AI assistant — extraordinary for writing, coding, and broad reasoning. Exmergo Viz is the purpose-built AI agent for data visualization: grounded, persistent, shareable, and governed. Use ChatGPT for the problems it's great at, and use Exmergo Viz when your team needs dashboards that outlive a chat session. ## Frequently Asked Questions **Can ChatGPT build interactive dashboards?** Not persistent, shareable ones. ChatGPT can produce charts inside a conversation, but those charts live in a transient chat thread and don't persist as structured dashboards with a stable URL. Exmergo Viz is purpose-built for persistent, shareable dashboards. **Is ChatGPT accurate for structured data analysis?** ChatGPT can analyze data but is prone to hallucination on numerical answers. Exmergo Viz grounds every answer in your actual data by generating structured queries that run against your files or database. **How is Exmergo's data privacy different from ChatGPT?** On Pro, Ultra, and Enterprise plans, Exmergo never uses your data, prompts, or schema to train AI models. Raw data files are not sent to third-party AI providers. ChatGPT's data usage policies vary by plan. **When should I use ChatGPT instead of Exmergo Viz?** Use ChatGPT for everyday writing, coding, brainstorming, and one-off data questions on small inputs. Use Exmergo Viz when you need recurring dashboards, non-technical users building them, shareable URLs, or governed enterprise data. **Does Exmergo Viz use ChatGPT under the hood?** No. Exmergo Viz uses Google Gemini as its underlying AI provider, orchestrated by agents purpose-built for data analysis. Customer data is not used to train models on paid tiers. --- # Exmergo Viz vs Claude — Which Is Right for You? > An honest comparison of Exmergo Viz and Claude. See where a purpose-built dashboard AI agent beats a general-purpose AI assistant — and where each fits. Claude is a remarkable general-purpose AI — strong at long-context reasoning, writing, and code. Exmergo Viz is the purpose-built AI agent for data visualization. ## At a Glance | Dimension | Exmergo Viz | Claude | |---|---|---| | Primary purpose | Building and sharing persistent, interactive dashboards | General-purpose AI assistant with long-context reasoning and Artifacts | | Output format | Interactive dashboards with stable shareable URLs | Chat messages and Artifacts — session-scoped documents, apps, and charts | | Data grounding | Structured queries against your actual data — results, not generated text | Python analysis tool can run against uploaded files; charting is code-driven | | Persistence | Dashboards persist, refresh, and reflect new data over time | Projects retain context; Artifacts don't refresh with new data as dashboards do | | Dashboard builder | Drag-and-drop dashboard builder with full style and layout control | No dashboard builder — output is code, documents, or Artifacts | | Data sources | CSV, Excel, SQL Server, MySQL, PostgreSQL | File uploads per conversation; MCP connectors for selected tools | | Sharing | One-click publish — anyone can view and interact, no account required | Artifact and project sharing — useful, but not the same as a live dashboard | | Pricing | Free tier, $19/mo Pro, $99/mo Ultra. Enterprise: custom pricing, no per-user tax. | Free tier, Pro $20/user/mo, Max from $100/user/mo, Team and Enterprise per-seat | | Built for | Recurring dashboards, non-technical users, governed enterprise data | Long-context reasoning, writing, coding, ad-hoc analysis | ## What Makes Exmergo Viz Different ### Agents Designed for the Visualization Workflow Exmergo's AI agents handle the full dashboard lifecycle: understand the question, validate the data, generate and run the query, build the chart, compose the dashboard. Not a general model with a chart feature — a system designed around the job. ### Interactive Dashboards, Not Chat Transcripts Output is a live, interactive dashboard at a stable URL — not a session-scoped Artifact. Dashboards persist, refresh, and can be embedded, published, or shared with anyone. ### Non-Technical Users Can Build & Explore Claude's analysis tool is powerful — but producing reusable dashboards typically requires someone who can read the generated code. In Exmergo, the user stays in the dashboarding UI. No code is shown, no code is needed. ### No Per-User Tax Exmergo's Enterprise plans include unlimited users. Your cost doesn't grow linearly with headcount the way per-seat AI pricing does. ## When Claude Is the Better Fit - You need a general-purpose AI for long-context reasoning, writing, coding, or working through complex problems end-to-end. - You're doing ad-hoc analysis where a Python notebook is exactly what you want — code, flexibility, and depth. - Your use case is document-heavy (contracts, research, codebases) and you want a model that can reason over hundreds of pages at a time. - Your team uses Claude as a coding or writing assistant and you want to keep the same tool for lightweight data exploration. ## When Exmergo Viz Is the Better Fit - You need dashboards that persist between sessions, refresh with new data, and live at a stable URL for anyone to open. - Non-technical users on your team need to build and explore dashboards without reading generated code. - You need governed enterprise data — no training on customer data, physical isolation options, and clear data-to-dashboard lineage. - You want one-click publishing and sharing — dashboards a leader can open from an email link without logging in anywhere. - You care about predictable pricing for a team or organization rather than per-seat licensing that scales with headcount. ## The Bottom Line Claude is an exceptional general-purpose AI — especially for long-context reasoning, coding, and ad-hoc analysis. Exmergo Viz is the purpose-built AI agent for data visualization: interactive dashboards, stable URLs, governed data, and a workflow designed so non-technical users can ship dashboards without learning to code. Use Claude where it shines. Use Exmergo Viz when your team needs dashboards. ## Frequently Asked Questions **Can Claude build and share interactive dashboards?** Claude can produce charts and analysis inside Artifacts, but Artifacts are session-scoped and not designed as persistent, multi-user dashboards with a stable URL. Exmergo Viz is purpose-built for persistent, shareable, interactive dashboards. **How does Claude's data grounding compare to Exmergo's?** Claude can run Python in its analysis tool against uploaded files, which gives it strong grounding for one-off analysis. Exmergo goes further for dashboards: it generates structured queries, validates the data, keeps a lineage of sources-to-dashboards, and surfaces results in an interactive UI. **Is Claude suitable for non-technical users to build ongoing dashboards?** Claude is approachable for chat and one-off analysis, but non-technical users generally don't end up with governed, shareable dashboards that stay alive between sessions. Exmergo is designed so a non-technical user can build, publish, and maintain a dashboard with no code. **When should I use Claude instead of Exmergo Viz?** Use Claude for long-context reasoning, writing, coding, and ad-hoc analysis. Use Exmergo Viz when you need recurring dashboards, a stable shareable URL, multi-user workspaces, or governed enterprise data. **Does Exmergo Viz use Claude under the hood?** No. Exmergo Viz uses Google Gemini as its underlying AI provider, orchestrated by agents purpose-built for data analysis and visualization. On paid tiers, customer data is not used to train AI models. --- # Data & Analytics Teams — Exmergo Viz > Empower your data team with AI-powered dashboards. Reduce ad-hoc requests, centralize data sources, and deliver insights in minutes instead of weeks. Exmergo Viz acts as your team's AI-powered first line of support. Business teams get the dashboards and answers they need instantly — your data team focuses on high-value work instead of ad-hoc requests. ## The Problem: Your Team Shouldn't Be a Help Desk Data teams are drowning in ad-hoc requests. Every stakeholder needs a dashboard, every exec wants a custom report, and your analysts spend more time fielding questions than doing actual analysis. The backlog grows. Requests take days or weeks. Business teams get frustrated. Your best people burn out on repetitive work instead of building the data infrastructure that actually moves the company forward. Exmergo Viz changes the equation. Business users get self-service dashboards powered by AI — accurate, governed, and ready in minutes. Your team gets its capacity back. ## Built for How Data Teams Actually Work ### Centralized Data Hub Upload data from CSV, Excel, or connect enterprise databases. One source of truth, reusable across every dashboard in your organization. ### AI-Powered Analysis Natural language queries that understand your data. Ask questions, get charts and insights — no SQL, no code, no waiting on analyst bandwidth. ### Governance & Security Role-based access, workspace-level permissions, and full data lineage. Your data stays governed even when everyone has access. ## What Your Team Gets - Reduce dashboard creation from weeks to minutes - Free your analysts to focus on high-value work - Give every stakeholder self-service access to governed data ## Frequently Asked Questions **How does Exmergo reduce the dashboard backlog?** Exmergo Viz acts as an AI-powered first line of support. Business users get self-service dashboards and natural-language answers instantly, which frees your data team from repetitive ad-hoc requests and shrinks the backlog. **Can non-technical users build governed dashboards in Exmergo?** Yes. Business users build dashboards by asking questions in plain English. RBAC, workspace-level permissions, and full data lineage keep everything governed — even when everyone has access. **Does Exmergo replace my data team?** No. Exmergo frees your data team from routine dashboarding so they can focus on infrastructure, modeling, and advanced analytics. Think of it as a capacity multiplier, not a replacement. **How is data lineage and traceability handled?** Every dashboard records its data sources, and every data source tracks which dashboards depend on it. You can search, filter, and navigate between sources and dashboards from a single data-management interface. **Can Exmergo connect to our enterprise data warehouse?** Enterprise plans support live connections to SQL Server, MySQL, and PostgreSQL. For warehouses like Snowflake, BigQuery, or Databricks, contact Exmergo sales to discuss connector roadmap and custom integrations. --- # Marketing Teams — Exmergo Viz > Turn marketing data into actionable dashboards. Connect campaign spend to revenue, track performance in real time, and build exec-ready reports with AI. Exmergo Viz turns your marketing data into clear, interactive dashboards. Track campaign performance, connect spend to revenue, and build exec-ready reports — all with AI, no analyst required. ## The Problem: Marketing Reporting Is Broken Your data lives in six different tools. Campaign metrics are in one place, revenue data in another, and customer data in a third. Every reporting cycle means hours of manual exports, spreadsheet wrangling, and slide formatting. By the time the dashboard is ready, the data is stale and the window to act has closed. Leadership asks questions you can't answer without another round of digging. Exmergo Viz centralizes your marketing data and lets you ask questions directly. Get real-time dashboards that connect campaign execution to business outcomes — and share them with leadership in one click. ## Marketing Intelligence, Not Marketing Guesswork ### Campaign Performance Dashboards Visualize spend, conversions, and ROI across every channel. Interactive charts that update in real time as your data changes. ### Revenue Attribution Connect marketing execution to financial outcomes. See which campaigns drive pipeline and which ones don't — backed by data, not gut feel. ### Exec-Ready Reporting Stop building slides manually. Create polished dashboards that leadership can explore on their own, and publish them with one click. ## What Your Marketing Team Gets - Connect campaign spend to revenue in real time - Build exec-ready marketing dashboards in minutes - Replace spreadsheet reporting with AI-powered analysis ## Frequently Asked Questions **Can Exmergo Viz connect to marketing platforms like HubSpot or Google Analytics?** HubSpot connects live on Enterprise plans. Google Analytics connectors are coming soon — until then, marketing teams typically upload CSV or Excel exports from Google Analytics, which Exmergo converts to structured data automatically. **How do I combine marketing spend with revenue data?** On Pro, Ultra, and Enterprise plans you can join multiple tables within a single dashboard. Upload or connect your campaign data and your revenue data, and ask Exmergo to attribute one to the other. **Can I build exec-ready marketing reports without a designer?** Yes. Exmergo generates polished, interactive dashboards from natural-language questions. One-click publishing creates a shareable link that leadership can explore on their own — no slide decks required. **Does Exmergo support multi-channel attribution?** Yes, when your data covers multiple channels. Ask Exmergo to break down conversions, spend, or ROI by channel and it will generate the appropriate visualization. **Can I share dashboards with agencies or external partners?** Yes. Published dashboards are read-only snapshots accessible via public link. Only aggregated query results are exposed — the raw data stays private. --- # Startups — Exmergo Viz > AI-powered dashboards for startups. Turn CSVs into investor-ready dashboards in minutes. No data team required. Start free. You don't have a data team — and you don't need one. Exmergo Viz turns your CSVs and spreadsheets into investor-ready dashboards with AI. Upload, ask, visualize. Start free. ## The Problem: You're Drowning in Spreadsheets Your data lives in CSV exports, Google Sheets, and email attachments. You need dashboards for your board deck, your investors want metrics, and your team needs visibility into what's working. But you don't have an analyst. And you definitely don't have budget for an enterprise BI tool. Exmergo Viz is built for exactly this. Upload a file, ask a question in plain English, and get a beautiful, interactive dashboard in minutes. Start for free — upgrade when you're ready. ## Ship Dashboards as Fast as You Ship Product ### Upload and Go Drop in a CSV or Excel file. Exmergo handles the rest — parsing, cleaning, and structuring your data automatically. ### AI Does the Analysis Ask questions in plain English. "Show me revenue by month" or "Which channel has the best conversion rate?" — the AI handles the query and builds the chart. ### Share with Anyone One-click publish creates a shareable link. Send polished dashboards to investors, board members, or your team — no login required for viewers. ## What Startups Get - Go from CSV to investor-ready dashboard in minutes - Replace your analyst hire with AI — starting at $0/month - Ship dashboards as fast as you ship product ## Frequently Asked Questions **Can I use Exmergo Viz for free?** Yes. The free tier includes 250 daily AI credits, unlimited dashboards, 15 GB of storage, and public sharing. No credit card required. Upgrade to Pro ($19/month) or Ultra ($99/month) when you outgrow it. **Is Exmergo suitable for investor reporting?** Yes. Upload a CSV of your metrics, ask Exmergo to build the visualizations, publish the dashboard, and share the link in your investor update. Many founders replace manual slide decks entirely. **Do I need a data team to use Exmergo?** No. Exmergo is built for teams without a dedicated analyst. Upload your data, ask questions in plain English, and get dashboards in minutes. **How do I share dashboards with my board or investors?** One-click publishing creates a read-only public link. Your viewers don't need an account or a login — they just open the link and interact with the dashboard. **Can Exmergo handle my customer, revenue, and product data in one place?** Yes. Upload files or connect databases into a centralized data hub, then build dashboards that span all of them. On Pro and above you can join tables within a single dashboard. --- # Recruitment Analytics with AI — Exmergo Viz > Exmergo Viz turns ATS exports into live hiring dashboards. Track time-to-fill, source-of-hire, and recruiter productivity with AI — no analyst, no backlog. Exmergo Viz turns your ATS exports into clear, interactive hiring dashboards. Track time-to-fill, source-of-hire, and recruiter productivity in minutes — not weeks. No SQL, no analyst, no backlog. ## The Problem: Your Hiring Funnel Is a Black Box Every recruiting leader knows the questions: which channels deliver our best hires, where do candidates drop off, how long does it really take to fill a role? The data is in your ATS — Greenhouse, Lever, Workday, Ashby — but getting it into a shape you can act on means CSV exports, spreadsheet wrangling, and a slow trickle of requests to the data team. By the time the funnel report lands in your inbox, the hiring plan has already shifted. Leadership asks what's working, and the honest answer is "we're checking." Exmergo Viz changes the rhythm. Drop in your ATS export, ask questions in plain English, and get the funnel, source-of-hire, and time-to-fill views leadership wants — live, interactive, and ready to share. ## Recruiting Intelligence, Not Recruiting Guesswork ### Funnel & Pipeline Dashboards Visualize conversion from applied to hired at every stage. Spot where candidates drop off, compare roles, and share an interactive funnel with your hiring managers. ### Source-of-Hire & Channel ROI See which channels, referrers, and agencies deliver hires that stick — backed by data, not recency bias. Shift spend toward what actually works. ### Time-to-Fill & Recruiter Productivity Track time-to-fill by role, team, and recruiter. Identify bottlenecks, workload imbalance, and stages where your process is losing time. ## What Your Recruiting Team Gets - Full-funnel hiring visibility — updated in minutes, not weeks - Data-backed decisions on source-of-hire and channel spend - Exec-ready reports without waiting on the data team ## Frequently Asked Questions **Which ATS platforms does Exmergo work with?** Exmergo works with any ATS that lets you export data. Recruiters typically export CSV reports from Greenhouse, Lever, Workday, Ashby, SmartRecruiters, or similar systems and upload them to Exmergo. The AI handles the parsing and structuring. **How do I measure time-to-fill and time-to-hire in Exmergo?** Upload your ATS data and ask Exmergo questions like "show me time-to-fill by role" or "trend time-to-hire over the last 6 months." The AI generates the appropriate charts without you writing any SQL or formulas. **Can I track source-of-hire and channel ROI?** Yes. With your sourcing and hiring data in Exmergo, you can ask for source-of-hire breakdowns, offer acceptance rates by channel, or cost-per-hire by source — and get interactive dashboards you can share with TA leadership. **Is Exmergo suitable for recruitment agencies?** Yes. Agencies use Exmergo to produce client-facing reports on placement velocity, submission-to-interview ratios, and pipeline health. Publish a dashboard and share a link with each client instead of building PowerPoint decks. **Can Exmergo help with diversity and pipeline analytics?** Yes, if your ATS data contains the relevant fields. Ask Exmergo to break down your pipeline by any dimension your data includes — stage, role, source, demographic attributes — and it will generate the visualization. --- # Supply Chain Analytics with AI — Exmergo Viz > Exmergo Viz turns ERP, WMS, and supplier data into real-time supply chain dashboards. Monitor OTIF, inventory, and supplier risk with AI — act before issues escalate. Exmergo Viz turns fragmented ERP, WMS, and spreadsheet data into real-time supply chain dashboards. Monitor OTIF, inventory, and supplier performance with AI — and catch issues before they become crises. ## The Problem: Your Data Moves Slower Than Your Supply Chain Operations runs on exports. PO data from the ERP. Receipt data from the WMS. Quality scores from a supplier scorecard that lives in Excel. By the time you've stitched it together, the OTIF miss is a week old and the post-mortem is already on the calendar. Meanwhile, inventory is either short or sitting, suppliers are missing promise dates, and the team is firefighting instead of forecasting. Exmergo Viz brings it together. Upload your operational exports or connect your databases, and ask Exmergo to surface what matters — OTIF by supplier, inventory by SKU, lead-time drift, defect trends — with dashboards your whole operations org can trust. ## Operations Visibility Without the Data-Team Wait ### Logistics & OTIF Dashboards Track on-time in-full by supplier, lane, and SKU. Spot late-delivery patterns early and share a live view with your ops and procurement leads. ### Inventory & Demand Visibility Visualize stock levels, turnover, and stockout risk across SKUs and locations. Compare planned vs. actual to keep forecasts honest. ### Supplier Performance & Risk Score suppliers on on-time delivery, defect rate, and cost variance. Consolidate scorecards into a single interactive dashboard — no more slide decks. ## What Your Operations Team Gets - Early anomaly detection across suppliers, inventory, and logistics - Cross-functional alignment on a single, trusted operations view - Weeks-to-minutes reporting — without new headcount ## Frequently Asked Questions **Can Exmergo visualize supply chain KPIs like OTIF, lead time, and fill rate?** Yes. Upload your fulfillment, shipment, or order data and ask Exmergo for OTIF by supplier, lead-time trends, or fill-rate by SKU. The AI generates interactive charts that update as your data refreshes. **Does Exmergo connect to ERP and WMS systems?** Exmergo supports live connections to SQL Server, MySQL, and PostgreSQL on Enterprise plans — common backends for ERP and WMS extracts. For systems like SAP or Oracle, teams typically export to a supported database or use scheduled CSV exports. **Can I build supplier performance dashboards?** Yes. Combine your PO, receipt, and quality data, then ask Exmergo to score suppliers by on-time delivery, defect rate, or cost variance. The dashboards are interactive and shareable with procurement and operations leadership. **Is Exmergo suitable for demand planning and forecasting?** Exmergo is strongest at descriptive and diagnostic analytics — visualizing historical demand, detecting anomalies, and comparing planned vs. actual. For statistical forecasting, teams typically run the forecast in their planning system and use Exmergo to visualize and monitor it. **Can operations teams use Exmergo without a data analyst?** Yes. Exmergo is built for operations and supply-chain teams who need visibility fast. Ask questions in plain English; the AI handles the query and chart generation. No SQL, no Python, no dedicated analyst required. --- # **Privacy Policy for Exmergo** *Last modified: August 16, 2026* ### **1. Introduction and Scope** This Privacy Policy describes how **Exmergo, Inc.** ("Exmergo," "we," "us," or "our"), a company incorporated in Delaware, United States, collects, uses, shares, and protects information. It applies to the Exmergo website at www.exmergo.com and to every Exmergo product. Our products have genuinely different architectures, so the details that matter to you depend on which one you use. Two product annexes carry those details: * [**Privacy Policy for Exmergo Viz**](/privacy/viz), our hosted analytics and dashboard service. * [**Privacy Policy for Exmergo Dex**](/privacy/dex), our open-source analytics engineering toolkit, which runs on your own machine. **Each annex forms part of this Privacy Policy and is incorporated into it by reference.** Where an annex is more specific than this document, the annex governs for that product. ### **2. Which Policy Applies to You** * **You visited our website.** This document applies in full. Nothing on the marketing site requires an account. * **You use Exmergo Viz.** This document applies, and the [Viz annex](/privacy/viz) describes how your uploaded data, prompts, dashboards, and connected sources are handled. * **You use Exmergo Dex.** This document applies only to what you send us directly, such as a support email or a GitHub issue. Dex runs entirely on your own machine and sends us nothing. The [Dex annex](/privacy/dex) sets out exactly where your data does and does not travel. ### **3. Our Role: Controller and Processor** Different data puts us in a different position, and the distinction matters for your rights and for our obligations. * **We are a controller** for information whose purposes and means of processing we decide: your account and profile information, billing records, support correspondence, and the usage data we collect on our website and inside Exmergo Viz. * **We are a processor** for the content you submit to Exmergo Viz. Files you upload, the prompts you write, and the results we compute from them are processed on your instructions and for your purposes. If that content includes personal data about other people, such as your own customers or employees, you are the controller of it and we act on your behalf. * **We are neither controller nor processor** for the data Exmergo Dex reads. Dex connects to your warehouse with your own credentials and returns results to your own agent. We have no access to that data, no copy of it, and no means of obtaining it. See the [Dex annex](/privacy/dex). A Data Processing Agreement covering our role as processor is available on request at legal@exmergo.com. ### **4. Information We Collect Across All Services** * **Account Information.** Your name, email address, and profile picture, received from Google or Microsoft when you sign in through them, together with your account settings and pricing tier. * **Billing Information.** Our payment processor, **Stripe, Inc.**, collects your card number, expiration date, and billing address directly. We do not store full payment card details on our servers. We receive and store limited billing records from Stripe, such as the last four digits of your card, the card brand, and your billing country, for account management and support. * **Support and Business Correspondence.** Messages you send to our support, sales, legal, or security addresses, and anything you choose to include in them. Product-specific collection is described in the annexes. ### **5. The Exmergo Website** Our marketing website collects the following automatically. None of it requires you to sign in, and none of it is tied to a Viz account unless you create one. * **Analytics.** We use **Google Analytics**, delivered through Google Firebase, to understand how the site is used. This records device and browser type, operating system, screen resolution, approximate geographic location such as country and city, how you arrived at the site, which pages you visited, how long you stayed, and which elements you interacted with. It includes a randomly generated client identifier stored in a first-party cookie so that repeat visits can be distinguished from new ones. * **Anonymous session identifier.** When you load the site, our application signs you in to **Firebase Authentication** as an anonymous user. This creates a session identifier used to operate interactive parts of the site. It is not linked to your name or email address, and it does not create an Exmergo Viz account. * **Server logs.** Our servers record technical information for security, abuse prevention, and debugging, which may include your IP address, request details, and timestamps. We do not operate advertising trackers, and we do not run third-party visitor identification or de-anonymization services on this site. **Your choices.** You can manage or clear cookies through your browser settings, and you can opt out of Google Analytics collection entirely by installing the [Google Analytics Opt-out Browser Add-on](https://tools.google.com/dlpage/gaoptout). ### **6. Sub-processors** We share information with the following service providers, only to the extent needed to operate our services: * **Google Cloud Platform and Firebase.** Hosting, file storage, our application database, website and product analytics, and the anonymous session identifier described above. * **Google (Gemini).** The AI models behind Exmergo Viz. What is and is not sent to them is set out precisely in the [Viz annex](/privacy/viz). * **Google and Microsoft (authentication).** When you sign in through a provider, you authenticate directly with them. We receive only basic profile information on success. * **Stripe, Inc.** Payment processing for paid plans. Stripe's handling of your payment data is governed by [Stripe's Privacy Policy](https://stripe.com/privacy). **Exmergo Dex has no sub-processors, because no data from Dex reaches Exmergo at all.** We may also disclose information where required by law, to enforce our agreements, to protect the rights and safety of our users, or in connection with a merger, acquisition, or sale of assets. If a change of control would place your information under a different privacy policy, we will notify you first. ### **7. How We Use Information, and On What Basis** | Purpose | Information used | Legal basis (where GDPR applies) | | --- | --- | --- | | Providing and operating the service | Account, uploaded content, prompts, dashboards | Performance of a contract | | Billing and collecting payment | Account, billing records | Performance of a contract | | Securing the service and preventing abuse | Server logs, usage data | Legitimate interests | | Debugging and improving reliability | Server logs, aggregated usage data | Legitimate interests | | Understanding product usage in aggregate | Analytics data | Consent, or legitimate interests where consent is not required | | Training and refining our AI models on free plans only | Prompts, data schema, data samples | Consent, given by choosing the free plan on the terms described in the [Viz annex](/privacy/viz) | | Sending service and account communications | Account information | Performance of a contract | | Complying with legal obligations | As required | Legal obligation | Paid Exmergo Viz plans are excluded from AI model training entirely. See section 6 of the [Viz annex](/privacy/viz). ### **8. Sharing and Sale of Personal Data** **We do not sell your personal data.** We do not share it for cross-context behavioral advertising, and we do not disclose it to data brokers. We share it only with the sub-processors named in section 6, and only for the purposes described there. ### **9. Security** We encrypt data in transit using HTTPS and at rest, we rely on the security infrastructure of Google Cloud Platform, and we segregate customer data logically so that one account cannot reach another's. Access to production systems is limited to personnel who need it. No system is perfectly secure. If you believe you have found a vulnerability in any Exmergo product, please write to security@exmergo.com. For Exmergo Dex, you may also file a private security advisory on the [GitHub repository](https://github.com/exmergo/dex/security/advisories/new). Please do not include real credentials or raw customer data in a report. ### **10. Retention** We retain account, billing, and correspondence records for as long as your account is active, and afterwards only as long as needed to meet legal, accounting, or dispute-resolution obligations. Retention of content you submit to a specific product is described in that product's annex. Analytics and server log data are retained on a rolling basis and are not kept indefinitely in identifiable form. ### **11. Your Privacy Rights** Subject to your location and applicable law, you may have the right to: * **Access** the personal information we hold about you, and receive a copy of it. * **Rectify** information that is inaccurate or incomplete. * **Erase** your personal information, subject to legal limitations. * **Port** your information in a structured, commonly used, machine-readable format. * **Restrict** how we process your information. * **Object** to processing carried out on the basis of legitimate interests. * **Withdraw consent** at any time, where processing is based on consent. Withdrawal does not affect processing already carried out. * **Be free from discrimination** for exercising any of these rights. You can manage much of this yourself inside Exmergo Viz, including renaming and deleting your files and dashboards. For anything else, write to support@exmergo.com. We will respond within the period required by applicable law, and we will not charge you for a reasonable request. You may authorize an agent to act for you, and you may lodge a complaint with your local supervisory authority. If you are a customer's end user and your personal data reached us because someone else uploaded it, please contact that organization first. They are the controller, and we will refer your request to them. ### **12. International Data Transfers** Our services are hosted and operated in the United States. Using them means your information may be processed and stored in the United States and in other countries where our sub-processors operate. Where we transfer personal data out of the European Economic Area, the United Kingdom, or Switzerland, we rely on the **European Commission's Standard Contractual Clauses**, together with the UK International Data Transfer Addendum where applicable, as the transfer mechanism, supported by additional technical and organizational measures. Storage location depends on your plan: * **Free, Pro, and Ultra plans.** All data, including uploaded files and account information, is processed and stored on servers in the United States. * **Enterprise plans.** You may select a specific geography, for example within the European Union, for storage and processing. Your enterprise agreement governs the specifics. ### **13. Children's Privacy** Our services are not directed to anyone under 16, and we do not knowingly collect personal information from children. If we learn that we have, we will delete it promptly. If you are a parent or guardian and believe your child has provided us with personal information, please contact us. ### **14. Governing Law** This Privacy Policy, and any dispute arising from it, is governed by the laws of the State of Delaware, United States, without regard to its conflict of law provisions. Nothing here limits rights you hold under the mandatory law of your own country of residence. ### **15. Changes to This Policy** We may update this Privacy Policy and its annexes from time to time. We will post the revised version here and update the date at the top. If a change materially affects how we handle your information, we will give you notice through the service or by email before it takes effect. ### **16. Contact Us** Exmergo, Inc. 1111B S Governors Ave # 58620, Dover, DE 19904, United States * General and privacy requests: support@exmergo.com * Legal, DPAs, and contracts: legal@exmergo.com * Security reports: security@exmergo.com --- ### **Annex A: Exmergo Viz** Exmergo Viz is a hosted service at viz.exmergo.com. You upload files or connect a data source, ask questions in plain English, and publish dashboards. We store your data, run queries against it, and send a bounded subset of it to Google's AI models to generate queries and visualizations. Your raw data file is never sent to those models. Free plans contribute prompts, schema, and samples to model training; paid plans never do. **Read the full annex: [Privacy Policy for Exmergo Viz](/privacy/viz).** ### **Annex B: Exmergo Dex** Exmergo Dex is an open-source toolkit that runs on your own machine, inside your own coding agent, using your own warehouse credentials. It has no Exmergo account, no Exmergo server, and no telemetry. Nothing about your data, your queries, or your usage is transmitted to Exmergo. Your data travels only to your warehouse and to the AI model provider your own agent is configured with, under your agreement with them. **Read the full annex: [Privacy Policy for Exmergo Dex](/privacy/dex).** --- # **Privacy Policy for Exmergo Viz** *Last modified: August 16, 2026* ### **1. Scope** This annex describes how **Exmergo, Inc.** handles data in **Exmergo Viz**, our hosted analytics and dashboard service at viz.exmergo.com. It forms part of the [Exmergo Privacy Policy](/privacy) and should be read with it. The main policy covers who we are, your rights, international transfers, security, retention of account records, and how to contact us. This annex covers what is specific to Viz. Where the two differ on a Viz question, this annex governs. Exmergo Dex is a different product with a different architecture and is covered by its own annex, the [Privacy Policy for Exmergo Dex](/privacy/dex). ### **2. Our Role for Exmergo Viz** * **We are a processor** for the content you put into Viz: the files you upload, the sources you connect, the prompts you write, and the dashboards you build. We process that content on your instructions, for your purposes. If it contains personal data about other people, you are the controller of it. * **We are a controller** for your account information, your billing records, and the usage and analytics data we collect about how you use the service. A Data Processing Agreement covering our role as processor is available on request at legal@exmergo.com. ### **3. What We Collect in Exmergo Viz** #### **A. Information you provide** * **Account information.** When you create an account through Google or Microsoft, we receive your name, email address, and profile picture from that provider. We store this alongside your Viz settings, including your pricing tier. * **Guest accounts.** If you use Viz without signing up, we create an anonymous account so your work persists within the session. If you later sign up, we may use a temporary migration key to attach that work to your new account. The key is short-lived and exists only for that transfer. * **Uploaded data.** The files you upload for analysis, in formats including CSV, XLSX, JSON, and Parquet. We do not inspect, restrict, or catalogue the contents of these files beyond what is needed to query them for you. * **Connected sources.** Where your plan supports it, the credentials and connection settings for a data source you choose to connect. See section 7. * **Prompts.** The questions and instructions you type into the chat interface. * **Payment information.** Collected directly by **Stripe, Inc.** We never receive or store your full card number. #### **B. Information generated as you work** * **AI-generated content.** The queries and visualization code our agents produce in response to your prompts. * **Dashboard and session data.** The configuration of your dashboards, including chart titles, sizes, and positions, and the history of your conversation with the AI for each session. #### **C. Information collected automatically** * **Usage and analytics data,** collected through Google Analytics: device and browser type, operating system, screen resolution, approximate location, how you arrived, which features you used, and session duration, with a randomly generated client identifier stored in a cookie. * **Server logs,** recording IP address, request details, and timestamps for security and debugging. ### **4. How Your Data Is Stored and Queried** * **Conversion and storage.** Files you upload are converted to Apache Parquet and stored privately on Google Cloud Platform. * **Segregation.** Each file is written to a storage path unique to your user ID and session ID. Your data is not co-mingled with any other customer's, and no query path exists from one account to another's storage. * **Querying.** Our data engine reads your files directly from that private location. Query results are computed inside our infrastructure and returned to your browser. * **Encryption.** Data is encrypted in transit over HTTPS and at rest. ### **5. What the AI Models Receive** This is the part of Viz that most people want a precise answer on, so here it is precisely. **We do not send your raw data file to Google or to any other AI provider.** The file stays in our storage and is queried by our own engine. To generate a relevant query or visualization, our agents send Google's Gemini models a bounded subset: 1. Your conversational prompt, for example "show me sales by region." 2. The conversation history for that session. 3. The **schema** of your data: column names and data types. 4. A random **sample of rows**, so the model can tell what the columns actually contain. 5. **Aggregated results** computed from your data, so the model can describe patterns and write insights. Items 4 and 5 mean that some values from your data do reach the model. We say so plainly rather than claim a boundary we do not hold. What the model never receives is the complete dataset, the underlying file, or your stored credentials. If your data is sensitive enough that a sample of rows must not leave our infrastructure, an Enterprise deployment is the right fit. See section 12, and speak to us before you upload. ### **6. AI Model Training** * **Free plan.** We may use your conversational prompts, data schema, and data samples to train and refine the performance of our AI agents. Choosing the free plan is how that consent is given, and you can withdraw it at any time by upgrading to a paid plan or by deleting your account. * **Pro, Ultra, and Enterprise plans.** **Your data, prompts, and schema are never used to train our AI models.** This is not a setting you need to find and switch off. It applies from the moment your paid plan begins. Separately from either case, we analyze usage data in aggregated and anonymized form to understand which features are used and to improve the product. That analysis cannot be traced back to an individual user or dataset. ### **7. Connected Data Sources and Their Credentials** Beyond file upload, which is available on every plan, Viz can connect directly to systems you already use. Availability depends on your plan: | Connector type | Sources | Available on | | --- | --- | --- | | File upload | CSV, XLSX, JSON, Parquet | All plans, including Free | | API connectors | HubSpot, Stripe | Pro, Ultra, and Enterprise | | Database connectors | SQL Server, MySQL, PostgreSQL | Enterprise only | When you connect a source, we store the connection settings and the credentials or access tokens needed to reach it. Those are encrypted at rest, are scoped to your account, and are never sent to an AI provider, never written into a dashboard, and never exposed to anyone you share a dashboard with. Connections are encrypted in transit. You can revoke a connection at any time from within Viz, which deletes the stored credential. Enterprise deployments can additionally place these connections behind VPN or VPC access controls. ### **8. Published and Shared Dashboards** Publishing a dashboard creates a **read-only public snapshot**. It does **not** make your uploaded file public. When you publish, our engine re-runs the specific queries behind each visualization on your dashboard and saves only the **final results** to a separate public location. Anyone with the link can view the resulting charts. They cannot access, query, download, or reconstruct the underlying dataset, and they cannot see any column you did not chart. Treat a published link as public. Anyone who has it can open it, so publish only aggregates you are comfortable making public, and unpublish from within Viz when you no longer want the link to work. ### **9. Retention and Deletion** * **Uploaded files.** Retained while your account is active. Deleting a file inside Viz permanently deletes it from our systems. * **Dashboards and session history.** Retained while your account is active, and deletable individually from within Viz. * **Published snapshots.** Retained until you unpublish the dashboard or delete it. * **Account, billing, and correspondence records.** Retained as described in section 10 of the [main policy](/privacy). Deleting your account removes your uploaded files, dashboards, and session history. We may retain billing records where accounting or tax law requires it. ### **10. Where Your Data Is Stored** * **Free, Pro, and Ultra plans.** All data is processed and stored in the United States. If you are outside the United States, using these plans means your information is transferred there. * **Enterprise plans.** You may select a geography, for example within the European Union, for storage and processing. Your enterprise agreement sets the specifics. Transfers out of the EEA, the UK, or Switzerland rely on the Standard Contractual Clauses, as described in section 12 of the [main policy](/privacy). ### **11. Sub-processors for Exmergo Viz** * **Google Cloud Platform and Firebase.** Hosting, file storage, the application database, and analytics. * **Google (Gemini).** The AI models, receiving only what section 5 describes. * **Google and Microsoft.** Authentication, when you sign in through them. * **Stripe, Inc.** Payment processing on paid plans. We do not sell your personal data and we do not share it for advertising. ### **12. Enterprise Deployment Options** Enterprise customers can change where Viz runs, which changes the answer to several of the questions above: * **Standard Cloud.** Shared infrastructure with logical isolation, the same architecture described throughout this annex. * **Private Managed Cloud.** Dedicated infrastructure with physical isolation and a geography of your choosing. * **On-Premise.** Viz runs inside your own environment. Your data does not reach Exmergo infrastructure at all, and our role narrows to the account and licensing information you provide us directly. Your enterprise agreement, and any Data Processing Agreement executed with it, governs where these differ from this annex. ### **13. Prohibited Data** As set out in our [Terms of Service](/terms), you may not upload data subject to specific regulatory regimes, including Protected Health Information under HIPAA or cardholder data under PCI-DSS, unless you have a separate written agreement with us covering it. Viz is not configured for those regimes by default, and uploading such data without that agreement puts it outside the protections either of us has committed to. ### **14. Contact** Questions about this annex, or requests to exercise your rights, go to support@exmergo.com. Data Processing Agreements and contractual questions go to legal@exmergo.com. The full contact details are in section 16 of the [main policy](/privacy). --- # **Privacy Policy for Exmergo Dex** *Last modified: August 16, 2026* ### **1. The Short Answer** **Exmergo Dex runs on your machine, inside your own coding agent, using your own warehouse credentials. Exmergo receives nothing.** There is no Dex account, no Exmergo server in the Dex path, no telemetry, no usage reporting, no licence check, and no update ping. Dex contains no code that sends anything to an Exmergo endpoint, because no such endpoint exists for it. Dex is [open source under Apache 2.0](https://github.com/exmergo/dex), so you do not have to take our word for any of this. That is the whole claim, and the rest of this page is the detail behind it. ### **2. Where Your Data Actually Goes** Dex is a toolkit your agent calls. Several parties can end up seeing something, and it matters which relationship each one sits in. This is the complete list. | Destination | What reaches it | Whose relationship | | --- | --- | --- | | **Your data warehouse** | Read-only SQL that Dex generates or that your agent authors | Yours. Your credentials, your infrastructure, your vendor agreement. | | **Your AI model provider**, through your agent | Schema, statistics, PII flags, and capped non-personal query results, as detailed in section 3 | Yours. Dex makes no model call of its own. | | **dbt Cloud Semantic Layer**, only if you opt in | Metric and dimension names, group-by tokens, and `where` clauses passed through as SQL. Aggregated rows come back. | Yours. Your dbt Cloud account and token. | | **dbt Labs**, during `dex transform build` | dbt-core's own anonymous usage statistics, sent by dbt itself | dbt Labs'. See section 6. | | **Your Python package index**, typically PyPI | A package resolve and download for the pinned `exmergo-dex-core` release | The index operator's. | | **Exmergo** | **Nothing.** | None exists. | The only entry Dex introduces on its own is the last row, and it is empty. ### **3. What Crosses into Your Agent's Context** This is the question a security review should actually ask, because whatever Dex hands your agent is then sent to whichever AI model provider that agent is configured with. Every Dex command returns exactly one sanitized JSON envelope. Nothing else crosses that boundary. **What can cross:** * **Structure.** Table and column names, data types, object types, row counts, and byte sizes. * **Statistics.** Null fractions, distinct counts, uniqueness and key findings, orphan fractions on inferred joins, and data-quality observations expressed as percentages. * **Minimum and maximum values, but only for columns that carry no personal-data flag and hold numeric, temporal, or boolean data.** A minimum of a text column is a raw value, and the minimum of a personal-data column is a sensitive one. Neither is ever computed. * **Value domains,** meaning up to 25 distinct values with their frequencies, and only for columns that carry no personal-data flag at any confidence, are not part of a key, and hold fewer distinct values than 10% of their rows. In practice this captures things like `status in (pending, shipped, cancelled)`. It cannot capture a high-cardinality or personal column. * **Query results,** only through the query firewall described in section 4, and capped at 50 rows, 256 characters per cell, and 16 KB per payload. * **Personal-data flags,** recorded strictly as a column name, a category, and a confidence score. **What can never cross:** * **Credentials.** The envelope sanitizer scans every payload for secret-shaped keys and raises an error rather than quietly stripping them, so a leak fails the command instead of shipping silently. * **Personal data values.** A flag has no field for an example value, so there is nowhere to put one even by accident. * **Raw rows.** The sanitizer rejects any row-shaped payload outright. Query results are returned column-wise for exactly this reason. ### **4. How Personal Data Is Detected and Blocked** Dex flags personal data **from column names and aggregate statistics, never by reading values.** Column names are matched against categories including email address, phone number, personal name, postal address, government identifier, financial identifier, credential, geographic coordinate, date of birth, and free text. Confidence is then adjusted using shape statistics computed inside SQL aggregates, so only numeric fractions ever leave your warehouse. Evidence can raise or lower a confidence score. **It can never clear a flag.** The only way to clear one is an explicit human entry in your own `.dex/config.yml`, which is re-applied on every profiling run and leaves an audit trail. Once a column is flagged at or above the blocking threshold, the query firewall enforces the following: * **Allowed over a flagged column:** measuring aggregates such as `COUNT`, `COUNT(DISTINCT ...)`, `AVG`, `SUM`, standard deviation, variance, and correlation. Their output is a statistic, not a value. `select count(distinct email) from customers` runs. * **Refused:** any row-level projection of a flagged column, and every value-carrying aggregate, including `MIN`, `MAX`, `ANY_VALUE`, `MODE`, percentiles, `STRING_AGG`, and `ARRAY_AGG`. `select email from customers` is refused. * **Unknown functions are treated as value-carrying,** so the gate fails closed rather than open. * **Reshaping does not launder anything.** Columns produced by `UNNEST`, `FLATTEN`, or `EXPLODE` inherit the flags of their inputs. * **An unprofiled table or column is refused,** because the firewall has no basis on which to allow it. * **Refusal messages carry no values.** They name the column and suggest unflagged alternatives, nothing more. The blocking threshold is a fixed constant compiled into the engine. It is deliberately not configurable, so no one can widen the personal-data boundary with a one-line edit to a committed config file. One consequence worth stating plainly: the firewall governs what a query **returns**, not what a query **filters on**. `WHERE` clauses, joins, and `GROUP BY` are unrestricted, because values flow into them rather than out of them. This matters for section 5. ### **5. What Dex Writes to Your Disk** Dex stores its state in a `.dex/` directory in your project. **This directory is designed to be committed to your repository**, so it is worth knowing exactly what is in it. | File | What it holds | | --- | --- | | `config.yml` | Connector targets, budgets, limits, and personal-data overrides. Non-secret by design. | | `cache.json` | The exploration map: structure, statistics, personal-data flags, and the bounded values described in section 3. | | `snapshot.json` | A frozen copy of the same, used as the baseline for drift detection. | | `drift.json` | The last drift report: counts, identifiers, and severities. | | `queries.jsonl` | An append-only decision ledger of every query attempt, storing **the SQL text verbatim**, along with the decision made. Never the results. | | `spend.jsonl` | An append-only billing ledger: byte counts, durations, job identifiers, and **hashed** statements. Never SQL text, never values. | | `plans/*.json` | Proposed dbt file changes awaiting your review. | Two things follow from this, and we would rather state them than let you discover them: 1. **The cache and the snapshot do contain some values derived from your warehouse**, specifically the minimums, maximums, and low-cardinality value domains described in section 3. They exclude anything flagged as personal data. It would be inaccurate to tell you that nothing from your warehouse is written to disk. 2. **`queries.jsonl` records SQL verbatim, and `WHERE` clauses are not restricted by the firewall.** If your agent writes `select count(*) from users where email = 'someone@example.com'`, that literal value is in the ledger, and if `.dex/` is committed, it is in your version control history. **No file in `.dex/` ever contains a credential.** ### **6. Third-Party Paths You Should Know About** Three of the destinations in section 2 are not Exmergo's and are worth calling out on their own. * **Your AI model provider.** Dex never calls a model. Your agent does. Claude Code, or whichever agent you run, sends context to the provider you configured, under the agreement you have with them, governed by their privacy policy and their data-retention and training terms. Exmergo is not a party to that relationship and has no visibility into it. What Dex contributes to that context is bounded by section 3. * **dbt Labs.** `dex transform build` invokes dbt on your machine. dbt-core sends its own anonymous usage statistics to dbt Labs, and Dex does not disable them. That telemetry is dbt's, not ours, and it is governed by dbt Labs' privacy policy. You can turn it off in your own dbt configuration, in the usual way. * **Your package index.** The agent skills launch Dex through a pinned package specification, which resolves against whichever Python package index you have configured, usually PyPI. That request tells the index which version you fetched, in the same way any `pip install` does. It tells Exmergo nothing. The **dbt Cloud Semantic Layer** backend is opt-in and off by default. When you enable it, metric names, dimension names, and filter expressions go to your own dbt Cloud host with your own token, and aggregated rows come back. Personal-data screening runs before the request is sent. This is also the one path where Dex's cost guard cannot apply, because execution happens on dbt Cloud rather than under Dex's control, and every result on that path says so. ### **7. Credentials** Dex **discovers** credentials and never asks for them. It reads them from the chains you already use: Application Default Credentials for BigQuery, `connections.toml` or the Snowflake environment, the Databricks SDK chain, the AWS credential chain for Redshift, `pg_service.conf` or `DATABASE_URL` for Postgres, `CLICKHOUSE_URL` for ClickHouse, or an existing dbt profile. A credential is held in memory for the duration of a connection and then discarded. It is never written to `.dex/`, never printed, never rendered into a generated dbt profile, which uses environment variable references instead, and it is stripped out of error messages before they are shown. The envelope sanitizer treats a credential crossing the output boundary as a failure rather than something to clean up. ### **8. Read-Only Against Your Data** Dex is read-only against your warehouse, enforced independently at three levels: the connection is opened read-only where the connector supports it, a SQL guard refuses any statement that is not a single read-only `SELECT` anywhere in its parse tree, including one hidden inside a CTE, and the query firewall applies on top of both. If the component that validates SQL is unavailable, guarded commands refuse to run rather than fall back to something weaker. Dex writes in exactly three places, none of them your data: the `.dex/` directory, dbt project files in your repository through a reviewable diff you approve, and dev-target builds, which refuse to run against a production target. ### **9. Our Role, Formally** * **For the data Dex reads from your warehouse, Exmergo is neither controller nor processor.** We do not determine the purposes or means of that processing, we do not carry it out on your behalf, and we could not access that data if asked. Dex is software you run, not a service we operate. * **For information you send us directly**, such as a support email, a GitHub issue, or a security report, Exmergo is the controller. That is covered by section 4 of the [main policy](/privacy). **Sub-processors for Dex: none.** No data from Dex reaches Exmergo, so there is nothing to pass on. Because we process no personal data on your behalf through Dex, a Data Processing Agreement covering Dex would have no subject matter. If your procurement process requires a written statement to that effect, write to legal@exmergo.com and we will provide one. If you also use Exmergo Viz, a DPA covering that service is available on the same address. ### **10. Verifying This Yourself** Every claim on this page is a statement about code you can read. Dex is published under Apache 2.0 at [github.com/exmergo/dex](https://github.com/exmergo/dex), and the guarantees described here are enforced by tests in that repository rather than by convention. If you find a way to violate any of them, we want to hear about it. Report privately through a [GitHub security advisory](https://github.com/exmergo/dex/security/advisories/new) or to security@exmergo.com. We aim to acknowledge within three business days. Please send a sanitized reproduction, never real credentials or real warehouse data. ### **11. Scope, Changes, and Contact** This annex forms part of the [Exmergo Privacy Policy](/privacy) and is incorporated into it by reference. The main policy covers who we are, your rights, and how to contact us. Exmergo Viz is a hosted service with a different architecture and is covered by its own annex, the [Privacy Policy for Exmergo Viz](/privacy/viz). If a future version of Dex introduces any path that sends data to Exmergo, we will update this annex before that version ships, and the change will be visible in the repository's history as well as here. Questions go to support@exmergo.com. Contractual questions go to legal@exmergo.com. Security reports go to security@exmergo.com. --- # Terms of Service — Exmergo > Read the Terms of Service for using the Exmergo website and services. This document outlines your responsibilities and our commitments. **Last modified: March 21, 2026** These Terms of Service govern your use of Exmergo Viz, operated by Exmergo, Inc., a Delaware-incorporated company. ## 1. Acceptance of Terms By accessing or using the Service, you agree to be bound by these Terms and our Privacy Policy. If you do not agree, you may not use the Service. ## 2. Description of the Service Exmergo Viz is a SaaS platform that allows users to upload data and use AI agents to generate insights, queries, and data visualizations. The Service includes features for creating, managing, and sharing dashboards. ## 3. User Accounts - You may register using email, Google, or Microsoft. - You are responsible for all activities under your account. - Account tiers: Free, Pro, Ultra (1-user individual licenses), and Enterprise (account-wide, unlimited users). ## 4. User Content You retain full ownership of data you upload. By uploading, you warrant that you own the data or have the necessary rights, and that it does not violate any third-party rights. **Prohibited data:** PHI under HIPAA and financial data under PCI-DSS are prohibited without a separate written agreement. ## 5. Acceptable Use You agree not to: - Reverse engineer or decompile the Service - Use the Service to build a competing product - Introduce malicious code - Attempt unauthorized access to the Service or its systems ## 6. Intellectual Property Exmergo, Inc. owns all rights to the Service. AI-generated content (visualizations, queries) created in your account is licensed to you for your own business purposes on a worldwide, perpetual, royalty-free basis. You are responsible for validating its accuracy. ## 7. Published Dashboards Published dashboards expose only query results — your raw data is never made public. You are responsible for ensuring published content is appropriate for public viewing. ## 8. Disclaimers THE SERVICE IS PROVIDED "AS IS." AI-GENERATED CONTENT MAY CONTAIN ERRORS OR INACCURACIES. YOU ARE SOLELY RESPONSIBLE FOR VALIDATING ALL GENERATED CONTENT BEFORE USE. ## 9. Limitation of Liability Exmergo, Inc.'s aggregate liability for all claims is capped at the greater of $100 or amounts paid in the past six months. ## 10. Fees & Subscriptions - Paid plans (Pro, Ultra) are billed monthly or annually. Subscriptions auto-renew. - Payments are non-refundable. - Pro and Ultra plans include a 14-day free trial; a valid payment method is required. - Enterprise plans are billed per a separate enterprise agreement. - Payment processing by Stripe, Inc. ## 11. Termination You may stop using the Service at any time. Exmergo, Inc. may suspend or terminate your account for violations of these Terms. Upon termination, your data will be permanently deleted. ## 12. Dispute Resolution & Arbitration Disputes are resolved by binding arbitration administered by the AAA under Consumer Arbitration Rules. Class-action waiver applies. You have a 30-day right to opt out by writing to legal@exmergo.com. ## 13. Governing Law Delaware law governs these Terms. ## 14. DMCA / Copyright Copyright infringement notices: copyright@exmergo.com — Exmergo, Inc., 1111B S Governors Ave # 58620, Dover, DE 19904. ## 15. Contact Exmergo, Inc. — support@exmergo.com